Argumentation is ubiquitous, and the development of argumentation machines could greatly assist humans in managing and navigating argumentation. However, the development of such systems is hindered by the lack of common standards and suitable tools, leading to ad-hoc solutions with little reuse value. Towards a more unified approach, we present an extensible microservice-based architecture for argumentation machines. Being built on the established gRPC framework, it provides strongly typed interfaces for the following services: (i) Argument Mining, (ii) Case-Based Reasoning on Arguments, (iii) Argument Retrieval and Ranking, and (iv) Quality Assessment of Arguments. Our system is designed to be extensible, allowing for easy integration of new tasks. We demonstrate the feasibility of our architecture via a proof-of-concept implementation and provide additional supplementary resources, such as a REST API gateway. Our contributions are publicly available on GitHub under the permissive MIT license.
title = {{{ArgServices}}: {{A Microservice-Based Architecture}} for {{Argumentation Machines}}},
shorttitle = {{{ArgServices}}},
booktitle = {Robust {{Argumentation Machines}}},
author = {{Lenz}, {Mirko} and {Dumani}, {Lorik} and {Schenkel}, {Ralf} and {Bergmann}, {Ralph}},
editor = {{Cimiano}, {Philipp} and {Frank}, {Anette} and {Kohlhase}, {Michael} and {Stein}, {Benno}},
series = {Lecture {{Notes}} in {{Computer Science}}},
volume = {14638},
pages = {352--369},
publisher = {Springer Nature Switzerland},
location = {Cham},
doi = {10.1007/978-3-031-63536-6_21},
abstract = {Argumentation is ubiquitous, {and} the development of argumentation machines could greatly assist humans in managing {and} navigating argumentation. However, the development of such systems is hindered by the lack of common standards {and} suitable tools, leading to ad-hoc solutions with little reuse value. Towards a more unified approach, we present an extensible microservice-based architecture for argumentation machines. Being built on the established gRPC framework, it provides strongly typed interfaces for the following services: (i) Argument Mining, (ii) Case-Based Reasoning on Arguments, (iii) Argument Retrieval {and} Ranking, {and} (iv) Quality Assessment of Arguments. Our system is designed to be extensible, allowing for easy integration of new tasks. We demonstrate the feasibility of our architecture via a proof-of-concept implementation {and} provide additional supplementary resources, such as a REST API gateway. Our contributions are publicly available on GitHub under the permissive MIT license.},
eventtitle = {{{RATIO}} 2024},
isbn = {978-3-031-63536-6},
langid = {usenglish}
}
CBRkit: An Intuitive Case-Based Reasoning Toolkit for Python
Mirko Lenz, Lukas Malburg, and Ralph Bergmann
Case-Based Reasoning Research and Development, Lecture Notes in Computer Science, Vol. 14775, pp. 289-304, Springer Nature Switzerland
Developing Case-Based Reasoning (CBR) applications is a complex and demanding task that requires a lot of experience and a deep understanding of users. Additionally, current CBR frameworks are not as usable as Machine Learning (ML) frameworks that can be deployed with only a few lines of code. To address these problems and allow users to easily build hybrid Artificial Intelligence (AI) systems by combining CBR with techniques such as ML, we present the CBRkit library in this paper. CBRkit is a Python-based framework that provides generic and easily extensible functions to simplify the creation of CBR applications with advanced similarity measures and case representations. The framework is available from GitHub and PyPI under the permissive MIT license. An initial user study indicates that it is easily possible even for non-CBR experts and users who only have limited Python programming skills to develop their own customized CBR application.
BibTeX
@inproceedings{Lenz2024CBRkitIntuitiveCaseBased,
date = {2024},
title = {{{CBRkit}}: {{An Intuitive Case-Based Reasoning Toolkit}} for {{Python}}},
author = {{Lenz}, {Mirko} and {Malburg}, {Lukas} and {Bergmann}, {Ralph}},
editor = {{Recio-Garcia}, {Juan A.} and {Orozco-del-Castillo}, {Mauricio G.} and {Bridge}, {Derek}},
series = {Lecture {{Notes}} in {{Computer Science}}},
volume = {14775},
pages = {289--304},
publisher = {Springer Nature Switzerland},
location = {Cham},
doi = {10.1007/978-3-031-63646-2_19},
abstract = {Developing Case-Based Reasoning (CBR) applications is a complex {and} demanding task that requires a lot of experience {and} a deep understanding of users. Additionally, current CBR frameworks are not as usable as Machine Learning (ML) frameworks that can be deployed with only a few lines of code. To address these problems {and} allow users to easily build hybrid Artificial Intelligence (AI) systems by combining CBR with techniques such as ML, we present the CBRkit library in this paper. CBRkit is a Python-based framework that provides generic {and} easily extensible functions to simplify the creation of CBR applications with advanced similarity measures {and} case representations. The framework is available from GitHub {and} PyPI under the permissive MIT license. An initial user study indicates that it is easily possible even for non-CBR experts {and} users who only have limited Python programming skills to develop their own customized CBR application.},
eventtitle = {{{ICCBR}} 2024},
isbn = {978-3-031-63646-2},
langid = {usenglish},
annotation = {Best Student Paper Award at ICCBR 2024}
}
PolArg: Unsupervised Polarity Prediction of Arguments in Real-Time Online Conversations
Mirko Lenz and Ralph Bergmann
Robust Argumentation Machines, Lecture Notes in Computer Science, Vol. 14638, pp. 108-126, Springer Nature Switzerland
The increasing usage of social networks has led to a growing number of discussions on the Internet that are a valuable source of argumentation that occurs in real time. Such conversations are often made up of a large number of participants and are characterized by a fast pace. Platforms like X/Twitter and Hacker News (HN) allow users to respond to other users’ posts, leading to a tree-like structure. Previous work focused on training supervised models on datasets obtained from debate portals like Kialo where authors provide polarity labels (i.e., support/attack) together with their posts. Such classifiers may yield suboptimal predictions for the noisier posts from X or HN, so we propose unsupervised prompting strategies for large language models instead. Our experimental evaluation found this approach to be more effective for X conversations than a model fine-tuned on Kialo debates, but less effective for HN posts (which are more technical and less argumentative). Finally, we provide an open-source application for converting discussions on these platforms into argument graphs.
title = {{{PolArg}}: {{Unsupervised Polarity Prediction}} of {{Arguments}} in {{Real-Time Online Conversations}}},
shorttitle = {{{PolArg}}},
booktitle = {Robust {{Argumentation Machines}}},
author = {{Lenz}, {Mirko} and {Bergmann}, {Ralph}},
editor = {{Cimiano}, {Philipp} and {Frank}, {Anette} and {Kohlhase}, {Michael} and {Stein}, {Benno}},
series = {Lecture {{Notes}} in {{Computer Science}}},
volume = {14638},
pages = {108--126},
publisher = {Springer Nature Switzerland},
location = {Cham},
doi = {10.1007/978-3-031-63536-6_7},
abstract = {The increasing usage of social networks has led to a growing number of discussions on the Internet that are a valuable source of argumentation that occurs in real time. Such conversations are often made up of a large number of participants {and} are characterized by a fast pace. Platforms like X/Twitter {and} Hacker News (HN) allow users to respond to other users’ posts, leading to a tree-like structure. Previous work focused on training supervised models on datasets obtained from debate portals like Kialo where authors provide polarity labels (i.e., support/attack) together with their posts. Such classifiers may yield suboptimal predictions for the noisier posts from X or HN, so we propose unsupervised prompting strategies for large language models instead. Our experimental evaluation found this approach to be more effective for X conversations than a model fine-tuned on Kialo debates, but less effective for HN posts (which are more technical {and} less argumentative). Finally, we provide an open-source application for converting discussions on these platforms into argument graphs.},
eventtitle = {{{RATIO}} 2024},
isbn = {978-3-031-63536-6},
langid = {usenglish}
}
Tell Me Who You Are and I Tell You How You Argue: Predicting Stances and Arguments for Stakeholder Groups
Philipp Heinisch, Lorik Dumani, Philipp Cimiano, and Ralf Schenkel
Findings of the Association for Computational Linguistics: NAACL 2024, pp. 1968-1982, Association for Computational Linguistics
Argument mining has focused so far mainly on the identification, extraction, and formalization of arguments. An important yet unaddressedtask consists in the prediction of the argumentative behavior of stakeholders in a debate. Predicting the argumentative behavior in advance can support foreseeing issues in public policy making or help recognize potential disagreements early on and help to resolve them. In this paper, we consider the novel task of predicting the argumentative behavior of individual stakeholders. We present ARGENST, a framework that relies on a recommender-based architecture to predict the stance and the argumentative main point on a specific controversial topic for a given stakeholder, which is described in terms of a profile including properties related to demographic attributes, religious and political orientation, socio-economic background, etc. We evaluate our approach on the well-known debate.org dataset in terms of accuracy for predicting stance as well as in terms of similarity of the generated arguments to the ground truth arguments using BERTScore. As part of a case study, we show how juries of members representing different stakeholder groups and perspectives can be assembled to simulate the public opinion on a given topic.
BibTeX
@inproceedings{Heinisch2024TellMeWho,
date = {2024-06},
title = {Tell Me Who You Are {and} {{I}} Tell You How You Argue: {{Predicting Stances}} {and} {{Arguments}} for {{Stakeholder Groups}}},
shorttitle = {Tell Me Who You Are {and} {{I}} Tell You How You Argue},
booktitle = {Findings of the {{Association}} for {{Computational Linguistics}}: {{NAACL}} 2024},
author = {{Heinisch}, {Philipp} and {Dumani}, {Lorik} and {Cimiano}, {Philipp} and {Schenkel}, {Ralf}},
editor = {{Duh}, {Kevin} and {Gomez}, {Helena} and {Bethard}, {Steven}},
pages = {1968--1982},
publisher = {Association for Computational Linguistics},
abstract = {Argument mining has focused so far mainly on the identification, extraction, {and} formalization of arguments. An important yet unaddressedtask consists in the prediction of the argumentative behavior of stakeholders in a debate. Predicting the argumentative behavior in advance can support foreseeing issues in public policy making or help recognize potential disagreements early on {and} help to resolve them. In this paper, we consider the novel task of predicting the argumentative behavior of individual stakeholders. We present ARGENST, a framework that relies on a recommender-based architecture to predict the stance {and} the argumentative main point on a specific controversial topic for a given stakeholder, which is described in terms of a profile including properties related to demographic attributes, religious {and} political orientation, socio-economic background, etc. We evaluate our approach on the well-known debate.org dataset in terms of accuracy for predicting stance as well as in terms of similarity of the generated arguments to the ground truth arguments using BERTScore. As part of a case study, we show how juries of members representing different stakeholder groups {and} perspectives can be assembled to simulate the public opinion on a given topic.},
eventtitle = {Findings 2024}
}
2023
AQUAPLANE: The Argument Quality Explainer App
Sebastian Britner, Lorik Dumani, and Ralf Schenkel
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM '23, pp. 5015-5020, Association for Computing Machinery
In computational argumentation, so-called quality dimensions such as coherence or rhetoric are often used for ranking arguments. However, the literature often only predicts which argument is more persuasive, but not why this is the case. In this paper, we introduce AQUAPLANE, a transparent and easy-to-extend application that not only decides for a pair of arguments which one is more convincing with respect to a statement, but also provides an explanation.
abstract = {In computational argumentation, so-called quality dimensions such as coherence or rhetoric are often used for ranking arguments. However, the literature often only predicts which argument is more persuasive, but not why this is the case. In this paper, we introduce AQUAPLANE, a transparent {and} easy-to-extend application that not only decides for a pair of arguments which one is more convincing with respect to a statement, but also provides an explanation.},
isbn = {979-8-4007-0124-5}
}
Argument-Mining from Podcasts Using ChatGPT
Mircea-Luchian Pojoni, Lorik Dumani, and Ralf Schenkel
Proceedings of the Workshops at the 31st International Conference on Case-Based Reasoning (ICCBR-WS 2023), CEUR Workshop Proceedings, Vol. 3438, pp. 129-144, CEUR
Podcasts have emerged as a significant platform for the exchange of ideas, opinions, and knowledge on a variety of topics. At the same time, the extraction of arguments (called: argument mining) has received great attention. However, to the best of our knowledge, there exist no work that investigates the extraction of arguments from podcasts. One reason can be that podcasts often involve unpredictable and complex argument structures, and extracting valuable insights from them is challenging. In this work, we present the novel approach of extracting two different types of argumentative structures from podcast after transcribing them, i.e., (1) a simple but often used variant describing arguments as consisting of only a claim and a premise, where the claim describes the standpoint and the premise the reason to support or attack that claim and (2) an extended variant where an argument comprises premises, a main claim, counterarguments, and rebuttals. For this purpose, we utilize two specially designed prompts and OpenAI’s GPT-4 language model. For our test data, we chose three podcasts considering current computational constraints and the need for diversity in topics and discussion styles. Our evaluation shows the high feasibility of extracting arguments from podcasts using ChatGPT. We publish the podcasts’ transcripts as well as the extracted arguments.
title = {Argument-{{Mining}} from {{Podcasts Using ChatGPT}}},
booktitle = {Proceedings of the {{Workshops}} at the 31st {{International Conference}} on {{Case-Based Reasoning}} ({{ICCBR-WS}} 2023)},
author = {{Pojoni}, {Mircea-Luchian} and {Dumani}, {Lorik} and {Schenkel}, {Ralf}},
editor = {{Malburg}, {Lukas} and {Verma}, {Deepika}},
series = {{{CEUR Workshop Proceedings}}},
volume = {3438},
pages = {129--144},
publisher = {CEUR},
location = {Aberdeen, Scotland},
url = {https://ceur-ws.org/Vol-3438/#paper_10},
urldate = {2023-07-31},
abstract = {Podcasts have emerged as a significant platform for the exchange of ideas, opinions, {and} knowledge on a variety of topics. At the same time, the extraction of arguments (called: argument mining) has received great attention. However, to the best of our knowledge, there exist no work that investigates the extraction of arguments from podcasts. One reason can be that podcasts often involve unpredictable {and} complex argument structures, {and} extracting valuable insights from them is challenging. In this work, we present the novel approach of extracting two different types of argumentative structures from podcast after transcribing them, i.e., (1) a simple but often used variant describing arguments as consisting of only a claim {and} a premise, where the claim describes the standpoint {and} the premise the reason to support or attack that claim {and} (2) an extended variant where an argument comprises premises, a main claim, counterarguments, {and} rebuttals. For this purpose, we utilize two specially designed prompts {and} OpenAI’s GPT-4 language model. For our test data, we chose three podcasts considering current computational constraints {and} the need for diversity in topics {and} discussion styles. Our evaluation shows the high feasibility of extracting arguments from podcasts using ChatGPT. We publish the podcasts’ transcripts as well as the extracted arguments.},
Finding information online is hard, even more so once you get into the domain of argumentation. There have been developments around the specialized argumentation machines that incorporate structural features of arguments, but all current approaches share one pitfall: They operate on a corpora of limited sizes. Consequently, it may happen that a user searches for a rather general term like cost increases, but the machine is only able to serve arguments concerned with rent increases. We aim to bridge this gap by introducing approaches to generalize/specialize a found argument using a combination of WordNet and Large Language Models. The techniques are evaluated on a new benchmark dataset with diverse queries using our fully featured implementation. Both the dataset and the code are publicly available on GitHub.
author = {{Lenz}, {Mirko} and {Bergmann}, {Ralph}},
editor = {{Massie}, {Stewart} and {Chakraborti}, {Sutanu}},
series = {Lecture {{Notes}} in {{Computer Science}}},
volume = {14141},
pages = {263--278},
publisher = {Springer Nature Switzerland},
location = {Cham},
doi = {10.1007/978-3-031-40177-0_17},
abstract = {Finding information online is hard, even more so once you get into the domain of argumentation. There have been developments around the specialized argumentation machines that incorporate structural features of arguments, but all current approaches share one pitfall: They operate on a corpora of limited sizes. Consequently, it may happen that a user searches for a rather general term like cost increases, but the machine is only able to serve arguments concerned with rent increases. We aim to bridge this gap by introducing approaches to generalize/specialize a found argument using a combination of WordNet {and} Large Language Models. The techniques are evaluated on a new benchmark dataset with diverse queries using our fully featured implementation. Both the dataset {and} the code are publicly available on GitHub.},
eventtitle = {{{ICCBR}} 2023},
isbn = {978-3-031-40177-0},
langid = {usenglish},
annotation = {Best Student Paper Award at ICCBR 2023}
}
CLEARNESS: Coreference Resolution for Generating and Ranking Arguments Extracted from Debate Portals for Queries
Johannes Weidmann, Lorik Dumani, and Ralf Schenkel
Trust Me, I Am an Expert: Predicting the Credibility of Experts for Statements
Markus Nilles, Lorik Dumani, Björn Metzler, and Ralf Schenkel
Proceedings of the Workshops at the 31st International Conference on Case-Based Reasoning (ICCBR-WS 2023), CEUR Workshop Proceedings, Vol. 3438, pp. 114-128, CEUR
Nowadays, information on any topic can be researched on the Internet. However, in addition to reputable news sources, there is also a great deal of fake news that is disseminated, e.g., via social media or in established newspapers. Thus, the veracity must be assessed for each piece of information. People, parties, and organizations want to push through their interests and sometimes do not hesitate to spread fake news. For some time now, one popular means has been to quote (supposed) experts in a field. For example, —due to his authority— Albert Einstein is often quoted by believers in God although he was primarily concerned with physics while his quotes on God are taken out of context. In this paper, we define a new task of expert suitability prediction and evaluate methods to assess the credibility of a person with reference to a statement and its context and compare it to state-of-the-art approaches applying transformer-based embeddings. In an R4 cycle in CBR this approach could be used for the ranking. In this pilot study, we restrict our experiments to researchers, which allows us to derive their expertise from their publications. Furthermore, we make a manually labeled dataset consisting of 1,700 (statement,expert) pairs where suitable experts were tediously searched out together with valuable context information (such as convincing text parts of the experts’ contexts towards a statement) publicly available to stimulate further research in this very important, but up to now underrepresented area of fake news detection.
BibTeX
@inproceedings{Nilles2023TrustMeAm,
date = {2023-07-17},
title = {Trust Me, {{I}} Am an {{Expert}}: {{Predicting}} the {{Credibility}} of {{Experts}} for {{Statements}}},
shorttitle = {Trust Me, {{I}} Am an {{Expert}}},
booktitle = {Proceedings of the {{Workshops}} at the 31st {{International Conference}} on {{Case-Based Reasoning}} ({{ICCBR-WS}} 2023)},
author = {{Nilles}, {Markus} and {Dumani}, {Lorik} and {Metzler}, {Björn} and {Schenkel}, {Ralf}},
editor = {{Malburg}, {Lukas} and {Verma}, {Deepika}},
series = {{{CEUR Workshop Proceedings}}},
volume = {3438},
pages = {114--128},
publisher = {CEUR},
location = {Aberdeen, Scotland},
url = {https://ceur-ws.org/Vol-3438/#paper_09},
urldate = {2023-07-31},
abstract = {Nowadays, information on any topic can be researched on the Internet. However, in addition to reputable news sources, there is also a great deal of fake news that is disseminated, e.g., via social media or in established newspapers. Thus, the veracity must be assessed for each piece of information. People, parties, {and} organizations want to push through their interests {and} sometimes do not hesitate to spread fake news. For some time now, one popular means has been to quote (supposed) experts in a field. For example, —due to his authority— Albert Einstein is often quoted by believers in God although he was primarily concerned with physics while his quotes on God are taken out of context. In this paper, we define a new task of expert suitability prediction {and} evaluate methods to assess the credibility of a person with reference to a statement {and} its context {and} compare it to state-of-the-art approaches applying transformer-based embeddings. In an R4 cycle in CBR this approach could be used for the ranking. In this pilot study, we restrict our experiments to researchers, which allows us to derive their expertise from their publications. Furthermore, we make a manually labeled dataset consisting of 1,700 (statement,expert) pairs where suitable experts were tediously searched out together with valuable context information (such as convincing text parts of the experts’ contexts towards a statement) publicly available to stimulate further research in this very important, but up to now underrepresented area of fake news detection.},
Comparing Unsupervised Algorithms to Construct Argument Graphs
Mirko Lenz, Lorik Dumani, and Premtim Sahitaj
Joint Proceedings of Workshops, Tutorials and Doctoral Consortium Co-Located with the 45th German Conference on Artificial Intelligence, CEUR Workshop Proceedings, Vol. 3457, CEUR
Computational argumentation has gained considerable attention in recent years. Various areas have been addressed, such as extracting arguments from natural language texts into a structured form in order to store them in an argument base, determining stances for arguments with respect to topics, determination of inferences from statements, and much more. After so much progress has been made in the isolated tasks, in this paper we address the next level and aim to advance the automatic generation of argument graphs. To this end, we investigate various unsupervised methods for constructing the graphs and measure the performance with different metrics on three different datasets. Our implementation is publicly available on GitHub under the permissive MIT license.
title = {Comparing {{Unsupervised Algorithms}} to {{Construct Argument Graphs}}},
booktitle = {Joint {{Proceedings}} of {{Workshops}}, {{Tutorials}} {and} {{Doctoral Consortium}} Co-Located with the 45th {{German Conference}} on {{Artificial Intelligence}}},
author = {{Lenz}, {Mirko} and {Dumani}, {Lorik} and {Sahitaj}, {Premtim}},
editor = {{Koert}, {Dorothea} and {Minor}, {Mirjam}},
series = {{{CEUR Workshop Proceedings}}},
volume = {3457},
publisher = {CEUR},
location = {Virtual Event, Trier},
url = {https://ceur-ws.org/Vol-3457/#paper3tmg},
urldate = {2023-10-24},
abstract = {Computational argumentation has gained considerable attention in recent years. Various areas have been addressed, such as extracting arguments from natural language texts into a structured form in order to store them in an argument base, determining stances for arguments with respect to topics, determination of inferences from statements, {and} much more. After so much progress has been made in the isolated tasks, in this paper we address the next level {and} aim to advance the automatic generation of argument graphs. To this end, we investigate various unsupervised methods for constructing the graphs {and} measure the performance with different metrics on three different datasets. Our implementation is publicly available on GitHub under the permissive MIT license.},
In this paper, we present QualiAssistant, a free and open-source system written in Java for identification and extraction of Qualia structures from any natural language texts having many application scenarios such as argument mining or creating dictionaries. It answers the call for a Qualia bootstrapping tool with a ready-to-use system that can be gradually filled by the community with patterns in multiple languages. Qualia structures express the meaning of lexical items. They describe, e.g., of what kind the item is (formal role), what it includes (constitutive role), how it is brought about (agentive role), and what it is used for (telic role). They are also valuable for various Information Retrieval and NLP tasks. Our application requires search patterns for Qualia structures consisting of POS tag sequences as well as the dataset the user wants to search for Qualias. Samples for both are provided alongside this paper. While samples are in German, QualiAssistant can process all languages for which constituency trees can be generated and patterns are available. Our provided patterns follow a high-precision low-recall design aiming to generate automatic annotations for text mining but can be exchanged easily for other purposes. Our evaluation shows that QualiAssistant is a valuable and reliable tool for finding Qualia structures in unstructured texts.
abstract = {In this paper, we present QualiAssistant, a free {and} open-source system written in Java for identification {and} extraction of Qualia structures from any natural language texts having many application scenarios such as argument mining or creating dictionaries. It answers the call for a Qualia bootstrapping tool with a ready-to-use system that can be gradually filled by the community with patterns in multiple languages. Qualia structures express the meaning of lexical items. They describe, e.g., of what kind the item is (formal role), what it includes (constitutive role), how it is brought about (agentive role), {and} what it is used for (telic role). They are also valuable for various Information Retrieval {and} NLP tasks. Our application requires search patterns for Qualia structures consisting of POS tag sequences as well as the dataset the user wants to search for Qualias. Samples for both are provided alongside this paper. While samples are in German, QualiAssistant can process all languages for which constituency trees can be generated {and} patterns are available. Our provided patterns follow a high-precision low-recall design aiming to generate automatic annotations for text mining but can be exchanged easily for other purposes. Our evaluation shows that QualiAssistant is a valuable {and} reliable tool for finding Qualia structures in unstructured texts.},
eventtitle = {{{ArgMining-COLING}} 2022}
}
User-Centric Argument Mining with ArgueMapper and Arguebuf
Mirko Lenz and Ralph Bergmann
Computational Models of Argument, Frontiers in Artificial Intelligence and Applications, Vol. 353, pp. 367-368, IOS Press
Existing tools to create argument graphs are tailored for experts in the domain of argumentation. By taking into account the needs of experts, laymen, and developers, we propose ArgueMapper as a novel argument diagramming tool and Arguebuf as its underlying format. ArgueMapper is the first of its kind to be optimized for mobile devices and provide a discoverable interface suitable for novice users. Arguebuf provides native implementations for all major programming languages via a code generation approach. To complement Arguebuf, we provide a supercharged Python implementation that enables advanced analysis. All of our contributions support AIF and are publicly available on GitHub under the MIT license.
BibTeX
@inproceedings{Lenz2022UserCentricArgumentMining,
date = {2022},
title = {User-{{Centric Argument Mining}} with {{ArgueMapper}} {and} {{Arguebuf}}},
booktitle = {Computational {{Models}} of {{Argument}}},
author = {{Lenz}, {Mirko} and {Bergmann}, {Ralph}},
series = {Frontiers in {{Artificial Intelligence}} {and} {{Applications}}},
abstract = {Existing tools to create argument graphs are tailored for experts in the domain of argumentation. By taking into account the needs of experts, laymen, {and} developers, we propose ArgueMapper as a novel argument diagramming tool {and} Arguebuf as its underlying format. ArgueMapper is the first of its kind to be optimized for mobile devices {and} provide a discoverable interface suitable for novice users. Arguebuf provides native implementations for all major programming languages via a code generation approach. To complement Arguebuf, we provide a supercharged Python implementation that enables advanced analysis. All of our contributions support AIF {and} are publicly available on GitHub under the MIT license.},
eventtitle = {International {{Conference}} on {{Computational Models}} of {{Argument}}},
langid = {usenglish}
}
Workshop on Text Mining and Generation (TMG): Preface
Mirko Lenz, Lorik Dumani, Alexander Bondarenko, and Shahbaz Syed
Joint Proceedings of Workshops, Tutorials and Doctoral Consortium Co-Located with the 45rd German Conference on Artificial Intelligence, CEUR Workshop Proceedings, Vol. 3457, CEUR
This paper is a report on the first Text Mining and Generation Workshop (TMG), which was a one-day virtual event hosted at the German Conference on Artificial Intelligence (KI 2022) in Trier, Germany. In addition to four accepted original papers, there were three invited talks by speakers who presented their works already published at high-ranked conferences as well as one keynote by a pioneer in the two research fields relevant to the workshop.
BibTeX
@inproceedings{Lenz2022WorkshopTextMining,
date = {2022-09-19},
title = {Workshop on {{Text Mining}} {and} {{Generation}} ({{TMG}}): {{Preface}}},
booktitle = {Joint {{Proceedings}} of {{Workshops}}, {{Tutorials}} {and} {{Doctoral Consortium}} Co-Located with the 45rd {{German Conference}} on {{Artificial Intelligence}}},
author = {{Lenz}, {Mirko} and {Dumani}, {Lorik} and {Bondarenko}, {Alexander} and {Syed}, {Shahbaz}},
editor = {{Koert}, {Dorothea} and {Minor}, {Mirjam}},
abstract = {This paper is a report on the first Text Mining {and} Generation Workshop (TMG), which was a one-day virtual event hosted at the German Conference on Artificial Intelligence (KI 2022) in Trier, Germany. In addition to four accepted original papers, there were three invited talks by speakers who presented their works already published at high-ranked conferences as well as one keynote by a pioneer in the two research fields relevant to the workshop.},
Computational argumentation and especially argument mining together with retrieval enjoys increasing popularity. In contrast to standard search engines that focus on finding documents relevant to a query, argument retrieval aims at finding the best supporting and attacking premises given a query claim, e.g., from a predefined collection of arguments. Here, a claim is the central part of an argument representing the standpoint of a speaker with the goal to persuade the audience, and a premise serves as evidence to the claim. In addition to the actual retrieval process, existing work has focused on (1) classifying polarities of arguments into supporting or opposing, (2) classifying arguments by their frames (such as economic or environmental), and (3) clustering similar arguments by their meaning to avoid repetitions in the result list. For experiments, either hand-made argument collections or arguments extracted from debate portals were used. In this paper, we extend existing work on argument clustering, making the following contributions: First, we introduce a novel pipeline for clustering arguments. While previous work classified arguments either by polarity, frame, or meaning, our pipeline incorporates these three, allowing a more systematic presentation of arguments. Second, we introduce a new dataset consisting of 365 argument graphs accompanying more than 11,000 high-quality arguments that, contrary to previous datasets, have been generated, displayed, and verified by journalists and were published in newspapers. A thorough evaluation with this dataset provides a first baseline for future work.
BibTeX
@inproceedings{Dumani2021FineCoarseGranular,
date = {2021-10-26},
title = {Fine {and} {{Coarse Granular Argument Classification}} before {{Clustering}}},
booktitle = {Proceedings of the 30th {{ACM International Conference}} on {{Information}} {\&} {{Knowledge Management}}},
author = {{Dumani}, {Lorik} and {Wiesenfeldt}, {Tobias} and {Schenkel}, {Ralf}},
series = {{{CIKM}} '21},
pages = {422--432},
publisher = {Association for Computing Machinery},
location = {New York, NY, USA},
doi = {10.1145/3459637.3482431},
url = {https://doi.org/10.1145/3459637.3482431},
urldate = {2022-09-26},
abstract = {Computational argumentation {and} especially argument mining together with retrieval enjoys increasing popularity. In contrast to standard search engines that focus on finding documents relevant to a query, argument retrieval aims at finding the best supporting {and} attacking premises given a query claim, e.g., from a predefined collection of arguments. Here, a claim is the central part of an argument representing the standpoint of a speaker with the goal to persuade the audience, {and} a premise serves as evidence to the claim. In addition to the actual retrieval process, existing work has focused on (1) classifying polarities of arguments into supporting or opposing, (2) classifying arguments by their frames (such as economic or environmental), {and} (3) clustering similar arguments by their meaning to avoid repetitions in the result list. For experiments, either hand-made argument collections or arguments extracted from debate portals were used. In this paper, we extend existing work on argument clustering, making the following contributions: First, we introduce a novel pipeline for clustering arguments. While previous work classified arguments either by polarity, frame, or meaning, our pipeline incorporates these three, allowing a more systematic presentation of arguments. Second, we introduce a new dataset consisting of 365 argument graphs accompanying more than 11,000 high-quality arguments that, contrary to previous datasets, have been generated, displayed, {and} verified by journalists {and} were published in newspapers. A thorough evaluation with this dataset provides a first baseline for future work.},
isbn = {978-1-4503-8446-9}
}
QuARk: A GUI for Quality-Aware Ranking of Arguments
Markus Nilles, Lorik Dumani, and Ralf Schenkel
Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR '21, pp. 2546-2549, Association for Computing Machinery
With the Web augmenting every day and computers increasingly getting more powerful, research in the field of computational argumentation becomes more and more important. One of its research branches is argument retrieval, which aims at finding and presenting users the best arguments for their queries. Several systems already exist for this purpose, all having the same goal but reaching it in different ways. In line with existing work, an argument consists of a claim supported or attacked by a premise. Now that argument retrieval has become a separate task in the CLEF lab Touché, displaying the ranking is becoming increasingly important. In this paper we present QuARk, a GUI that allows users to retrieve arguments from a focused debate collection for their queries. Since we strictly distinguished between frontend and backend and kept the communication between them simple, QuARk can be extended to integrate various argument retrieval systems, assuming some modifications are made. In order to demonstrate the GUI, we show the integration of a complex retrieval algorithm that we also presented in the CLEF lab Touché. Our retrieval process consists of two parts. In the first step, it finds the most similar claims to the query. Therefore, the user can select between different standard IR similarity methods. The second step ranks the premises directly related to the claims. Therefore, the user can choose to rank the arguments either by quantitative, qualitative, or a combined measure.
BibTeX
@inproceedings{Nilles2021QuARkGUIQualityAware,
date = {2021-07-11},
title = {{{QuARk}}: {{A GUI}} for {{Quality-Aware Ranking}} of {{Arguments}}},
shorttitle = {{{QuARk}}},
booktitle = {Proceedings of the 44th {{International ACM SIGIR Conference}} on {{Research}} {and} {{Development}} in {{Information Retrieval}}},
author = {{Nilles}, {Markus} and {Dumani}, {Lorik} and {Schenkel}, {Ralf}},
series = {{{SIGIR}} '21},
pages = {2546--2549},
publisher = {Association for Computing Machinery},
location = {New York, NY, USA},
doi = {10.1145/3404835.3462795},
url = {https://doi.org/10.1145/3404835.3462795},
urldate = {2022-09-26},
abstract = {With the Web augmenting every day {and} computers increasingly getting more powerful, research in the field of computational argumentation becomes more {and} more important. One of its research branches is argument retrieval, which aims at finding {and} presenting users the best arguments for their queries. Several systems already exist for this purpose, all having the same goal but reaching it in different ways. In line with existing work, an argument consists of a claim supported or attacked by a premise. Now that argument retrieval has become a separate task in the CLEF lab Touché, displaying the ranking is becoming increasingly important. In this paper we present QuARk, a GUI that allows users to retrieve arguments from a focused debate collection for their queries. Since we strictly distinguished between frontend {and} backend {and} kept the communication between them simple, QuARk can be extended to integrate various argument retrieval systems, assuming some modifications are made. In order to demonstrate the GUI, we show the integration of a complex retrieval algorithm that we also presented in the CLEF lab Touché. Our retrieval process consists of two parts. In the first step, it finds the most similar claims to the query. Therefore, the user can select between different standard IR similarity methods. The second step ranks the premises directly related to the claims. Therefore, the user can choose to rank the arguments either by quantitative, qualitative, or a combined measure.},
isbn = {978-1-4503-8037-9}
}
The ReCAP Corpus: A Corpus of Complex Argument Graphs on German Education Politics
Lorik Dumani, Manuel Biertz, Alex Witry, Anna-Katharina Ludwig, Mirko Lenz, Stefan Ollinger, Ralph Bergmann, and Ralf Schenkel
IEEE Proceedings of the 15th International Conference on Semantic Computing (ICSC), pp. 248-255, IEEE
The automatic extraction of arguments from natural language texts is a highly researched area and more important than ever today, as it is nearly impossible to manually capture all arguments on a controversial topic in a reasonable amount of time. For testing different algorithms such as the retrieval of the best arguments, which are still in their infancy, gold standards must exist. An argument consists of a claim or standpoint that is supported or opposed by at least one premise. The generic term for a claim or premise is Argumentative Discourse Unit (ADU). The relationships between ADUs can be specified by argument schemes and can lead to large graphs. This paper presents a corpus of 100 argument graphs with about 2,500 ADUs in German, which is unique in its size and the utilisation of argument schemes. The corpus is built from natural language texts like party press releases and parliamentary motions on education policies in the German federal states. Each high-quality text is presented by an argument graph and created by the use of a modified version of the annotation tool OVA. The final argument graphs resulted by merging two previously independently annotated graphs based on detailed discussions.
BibTeX
@inproceedings{Dumani2021ReCAPCorpusCorpus,
date = {2021-01},
title = {The {{ReCAP Corpus}}: {{A Corpus}} of {{Complex Argument Graphs}} on {{German Education Politics}}},
shorttitle = {The {{ReCAP Corpus}}},
booktitle = {{{IEEE Proceedings}} of the 15th {{International Conference}} on {{Semantic Computing}} ({{ICSC}})},
author = {{Dumani}, {Lorik} and {Biertz}, {Manuel} and {Witry}, {Alex} and {Ludwig}, {Anna-Katharina} and {Lenz}, {Mirko} and {Ollinger}, {Stefan} and {Bergmann}, {Ralph} and {Schenkel}, {Ralf}},
pages = {248--255},
publisher = {IEEE},
location = {Laguna Hills, CA, USA},
doi = {10.1109/ICSC50631.2021.00083},
abstract = {The automatic extraction of arguments from natural language texts is a highly researched area {and} more important than ever today, as it is nearly impossible to manually capture all arguments on a controversial topic in a reasonable amount of time. For testing different algorithms such as the retrieval of the best arguments, which are still in their infancy, gold standards must exist. An argument consists of a claim or standpoint that is supported or opposed by at least one premise. The generic term for a claim or premise is Argumentative Discourse Unit (ADU). The relationships between ADUs can be specified by argument schemes {and} can lead to large graphs. This paper presents a corpus of 100 argument graphs with about 2,500 ADUs in German, which is unique in its size {and} the utilisation of argument schemes. The corpus is built from natural language texts like party press releases {and} parliamentary motions on education policies in the German federal states. Each high-quality text is presented by an argument graph {and} created by the use of a modified version of the annotation tool OVA. The final argument graphs resulted by merging two previously independently annotated graphs based on detailed discussions.},
eventtitle = {{{IEEE}} 15th {{International Conference}} on {{Semantic Computing}} ({{ICSC}})},
langid = {usenglish}
}
2020
A Framework for Argument Retrieval
Lorik Dumani, Patrick J. Neumann, and Ralf Schenkel
Advances in Information Retrieval, Lecture Notes in Computer Science, pp. 431-445, Springer International Publishing
Computational argumentation has recently become a fast growing field of research. An argument consists of a claim, such as “We should abandon fossil fuels”, which is supported or attacked by at least one premise, for example “Burning fossil fuels is one cause for global warming”. From an information retrieval perspective, an interesting task within this setting is finding the best supporting and attacking premises for a given query claim from a large corpus of arguments. Since the same logical premise can be formulated differently, the system needs to avoid retrieving duplicate results and thus needs to use some form of clustering. In this paper we propose a principled probabilistic ranking framework for premises based on the idea of tf-idf that, given a query claim, first identifies highly similar claims in the corpus, and then clusters and ranks their premises, taking clusters of claims as well as the stances of query and premises into account. We compare our approach to a baseline system that uses BM25F which we outperform even with a primitive implementation of our framework utilising BERT.
title = {A {{Framework}} for {{Argument Retrieval}}},
booktitle = {Advances in {{Information Retrieval}}},
author = {{Dumani}, {Lorik} and {Neumann}, {Patrick J.} and {Schenkel}, {Ralf}},
editor = {{Jose}, {Joemon M.} and {Yilmaz}, {Emine} and {Magalhães}, {João} and {Castells}, {Pablo} and {Ferro}, {Nicola} and {Silva}, {Mário J.} and {Martins}, {Flávio}},
series = {Lecture {{Notes}} in {{Computer Science}}},
pages = {431--445},
publisher = {Springer International Publishing},
location = {Cham},
doi = {10.1007/978-3-030-45439-5_29},
abstract = {Computational argumentation has recently become a fast growing field of research. An argument consists of a claim, such as “We should abandon fossil fuels”, which is supported or attacked by at least one premise, for example “Burning fossil fuels is one cause for global warming”. From an information retrieval perspective, an interesting task within this setting is finding the best supporting {and} attacking premises for a given query claim from a large corpus of arguments. Since the same logical premise can be formulated differently, the system needs to avoid retrieving duplicate results {and} thus needs to use some form of clustering. In this paper we propose a principled probabilistic ranking framework for premises based on the idea of tf-idf that, given a query claim, first identifies highly similar claims in the corpus, {and} then clusters {and} ranks their premises, taking clusters of claims as well as the stances of query {and} premises into account. We compare our approach to a baseline system that uses BM25F which we outperform even with a primitive implementation of our framework utilising BERT.},
isbn = {978-3-030-45439-5},
langid = {usenglish}
}
Quality-Aware Ranking of Arguments
Lorik Dumani and Ralf Schenkel
Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM '20, pp. 335-344, Association for Computing Machinery
Argument search engines identify, extract, and rank the most important arguments for and against a given controversial topic. A number of such systems have recently been developed, usually focusing on classic information retrieval ranking methods that are based on frequency information. An important aspect that has been ignored so far by search engines is the quality of arguments. We present a quality-aware ranking framework for arguments already extracted from texts and represented as argument graphs, considering multiple established quality measures. An extensive evaluation with a standard benchmark collection demonstrates that taking quality into account significantly helps to improve retrieval quality for argument search. We also publish a dataset in which arguments with respect to topics were tediously annotated by humans with three widely accepted argument quality dimensions.
title = {Quality-{{Aware Ranking}} of {{Arguments}}},
booktitle = {Proceedings of the 29th {{ACM International Conference}} on {{Information}} {\&} {{Knowledge Management}}},
author = {{Dumani}, {Lorik} and {Schenkel}, {Ralf}},
series = {{{CIKM}} '20},
pages = {335--344},
publisher = {Association for Computing Machinery},
location = {Virtual Event, Ireland},
doi = {10.1145/3340531.3411960},
url = {https://doi.org/10.1145/3340531.3411960},
urldate = {2020-10-24},
abstract = {Argument search engines identify, extract, {and} rank the most important arguments for {and} against a given controversial topic. A number of such systems have recently been developed, usually focusing on classic information retrieval ranking methods that are based on frequency information. An important aspect that has been ignored so far by search engines is the quality of arguments. We present a quality-aware ranking framework for arguments already extracted from texts {and} represented as argument graphs, considering multiple established quality measures. An extensive evaluation with a standard benchmark collection demonstrates that taking quality into account significantly helps to improve retrieval quality for argument search. We also publish a dataset in which arguments with respect to topics were tediously annotated by humans with three widely accepted argument quality dimensions.},
isbn = {978-1-4503-6859-9}
}
Ranking Arguments by Combining Claim Similarity and Argument Quality Dimensions
Lorik Dumani and Ralf Schenkel
Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum, CEUR Workshop Proceedings, Vol. 2696, CEUR
Research on computational argumentation is currently being intensively investigated. The goal of this community is to find the best pro and con arguments for a user given topic either to form an opinion for oneself, or to persuade others to adopt a certain standpoint. While existing argument mining methods can find appropriate arguments for a topic, a correct classification into pro and con is not yet reliable. The same side stance classification task provides a dataset of argument pairs classified by whether or not both arguments share the same stance and does not need to distinguish between topic-specific pro and con vocabulary but only the argument similarity within a stance needs to be assessed. The results of our contribution to the task are build on a setup based on the BERT architecture. We fine-tuned a pre-trained BERT model for three epochs and used the first 512 tokens of each argument to predict if two arguments share the same stance.
BibTeX
@unpublished{Ollinger2020SameSideStance,
date = {2020-04-23},
title = {Same {{Side Stance Classification Task}}: {{Facilitating Argument Stance Classification}} by {{Fine-tuning}} a {{BERT Model}}},
author = {{Ollinger}, {Stefan} and {Dumani}, {Lorik} and {Sahitaj}, {Premtim} and {Bergmann}, {Ralph} and {Schenkel}, {Ralf}},
url = {http://arxiv.org/abs/2004.11163},
urldate = {2020-04-27},
abstract = {Research on computational argumentation is currently being intensively investigated. The goal of this community is to find the best pro {and} con arguments for a user given topic either to form an opinion for oneself, or to persuade others to adopt a certain standpoint. While existing argument mining methods can find appropriate arguments for a topic, a correct classification into pro {and} con is not yet reliable. The same side stance classification task provides a dataset of argument pairs classified by whether or not both arguments share the same stance {and} does not need to distinguish between topic-specific pro {and} con vocabulary but only the argument similarity within a stance needs to be assessed. The results of our contribution to the task are build on a setup based on the BERT architecture. We fine-tuned a pre-trained BERT model for three epochs {and} used the first 512 tokens of each argument to predict if two arguments share the same stance.}
}
Segmenting and Clustering Noisy Arguments
Lorik Dumani, Christin Katharina Kreutz, Manuel Biertz, Alex Witry, and Ralf Schenkel
Proceedings of the Conference "Lernen, Wissen, Daten, Analysen", CEUR Workshop Proceedings, Vol. 2738, pp. 23-34, CEUR
Automated argument retrieval for queries is desirable, e.g., as it helps in decision making or convincing others of certain actions. An argument consists of a claim supported or attacked by at least one premise. The claim describes a controversial viewpoint that should not be accepted without evidence given by premises. Premises are composed of Elementary Discourse Units (EDUs) which are their smallest contextual components. Oftentimes argument search engines find similar claims to a query first before returning their premises. Due to heterogeneous data sources, premises often appear repeatedly in different syntactic forms. From an information retrieval perspective, it is essential to rank premises relevant for a query claim highly in a duplicate-free manner. The main challenge in clustering them is to avoid redundancies as premises frequently address various aspects, i.e., consist of multiple EDUs. So, two tasks can be defined: segmentation of premises in EDUs and clustering of similar EDUs. In this paper we make two contributions: Our first contribution is the introduction of a noisy dataset with 480 premises for 30 queries crawled from debate portals which serves as a gold standard for the segmentation of premises into EDUs and the clustering of EDUs. Our second contribution consists of first baselines for the two mentioned tasks, for which we evaluated various methods. Our results show that an uncurated dataset is a major challenge and that clustering EDUs is only reasonable with premises as context information.
title = {Segmenting {and} {{Clustering Noisy Arguments}}},
booktitle = {Proceedings of the {{Conference}} "{{Lernen}}, {{Wissen}}, {{Daten}}, {{Analysen}}"},
author = {{Dumani}, {Lorik} and {Kreutz}, {Christin Katharina} and {Biertz}, {Manuel} and {Witry}, {Alex} and {Schenkel}, {Ralf}},
editor = {{Trabold}, {Daniel} and {Welke}, {Pascal} and {Piatkowski}, {Nico}},
series = {{{CEUR Workshop Proceedings}}},
volume = {2738},
pages = {23--34},
publisher = {CEUR},
location = {Online},
url = {https://ceur-ws.org/Vol-2738/#paper24},
urldate = {2023-11-27},
abstract = {Automated argument retrieval for queries is desirable, e.g., as it helps in decision making or convincing others of certain actions. An argument consists of a claim supported or attacked by at least one premise. The claim describes a controversial viewpoint that should not be accepted without evidence given by premises. Premises are composed of Elementary Discourse Units (EDUs) which are their smallest contextual components. Oftentimes argument search engines find similar claims to a query first before returning their premises. Due to heterogeneous data sources, premises often appear repeatedly in different syntactic forms. From an information retrieval perspective, it is essential to rank premises relevant for a query claim highly in a duplicate-free manner. The main challenge in clustering them is to avoid redundancies as premises frequently address various aspects, i.e., consist of multiple EDUs. So, two tasks can be defined: segmentation of premises in EDUs {and} clustering of similar EDUs. In this paper we make two contributions: Our first contribution is the introduction of a noisy dataset with 480 premises for 30 queries crawled from debate portals which serves as a gold standard for the segmentation of premises into EDUs {and} the clustering of EDUs. Our second contribution consists of first baselines for the two mentioned tasks, for which we evaluated various methods. Our results show that an uncurated dataset is a major challenge {and} that clustering EDUs is only reasonable with premises as context information.},
Ralph Bergmann, Manuel Biertz, Lorik Dumani, Mirko Lenz, Anna-Katharina Ludwig, Patrick J. Neumann, Stefan Ollinger, Premtim Sahitaj, Ralf Schenkel, and Alex Witry
Argumentation Machines search for arguments in natural language from information sources on the Web and reason with them on the knowledge level to actively support the deliberation and synthesis of arguments for a particular user query. The recap project is part of the Priority Program ratio and aims at novel contributions to and confluence of methods from information retrieval, knowledge representation, as well as case-based reasoning for the development of future argumentation machines. In this paper we summarise recent research results from the project. In particular, a new German corpus of 100 semantically annotated argument graphs from the domain of education politics has been created and is made available to the argumentation research community. Further, we discuss a comprehensive investigation in finding arguments and argument graphs. We introduce a probabilistic ranking framework for argument retrieval, i.e. for finding good premises for a designated claim. For finding argument graphs, we developed methods for case-based argument retrieval considering the graph structure of an argument together with textual and ontology-based similarity measures applied to claims, premises, and argument schemes.
BibTeX
@article{Bergmann2020ReCAPProject,
date = {2020-06-09},
title = {The {{ReCAP Project}}},
author = {{Bergmann}, {Ralph} and {Biertz}, {Manuel} and {Dumani}, {Lorik} and {Lenz}, {Mirko} and {Ludwig}, {Anna-Katharina} and {Neumann}, {Patrick J.} and {Ollinger}, {Stefan} and {Sahitaj}, {Premtim} and {Schenkel}, {Ralf} and {Witry}, {Alex}},
abstract = {Argumentation Machines search for arguments in natural language from information sources on the Web {and} reason with them on the knowledge level to actively support the deliberation {and} synthesis of arguments for a particular user query. The recap project is part of the Priority Program ratio {and} aims at novel contributions to {and} confluence of methods from information retrieval, knowledge representation, as well as case-based reasoning for the development of future argumentation machines. In this paper we summarise recent research results from the project. In particular, a new German corpus of 100 semantically annotated argument graphs from the domain of education politics has been created {and} is made available to the argumentation research community. Further, we discuss a comprehensive investigation in finding arguments {and} argument graphs. We introduce a probabilistic ranking framework for argument retrieval, i.e. for finding good premises for a designated claim. For finding argument graphs, we developed methods for case-based argument retrieval considering the graph structure of an argument together with textual {and} ontology-based similarity measures applied to claims, premises, {and} argument schemes.},
langid = {usenglish}
}
Towards an Argument Mining Pipeline Transforming Texts to Argument Graphs
Mirko Lenz, Premtim Sahitaj, Sean Kallenberg, Christopher Coors, Lorik Dumani, Ralf Schenkel, and Ralph Bergmann
Computational Models of Argument, Frontiers in Artificial Intelligence and Applications, Vol. 326, pp. 263-270, IOS Press
This paper tackles the automated extraction of components of argumentative information and their relations from natural language text. Moreover, we address a current lack of systems to provide a complete argumentative structure from arbitrary natural language text for general usage. We present an argument mining pipeline as a universally applicable approach for transforming German and English language texts to graph-based argument representations. We also introduce new methods for evaluating the performance based on existing benchmark argument structures. Our results show that the generated argument graphs can be beneficial to detect new connections between different statements of an argumentative text.
BibTeX
@inproceedings{Lenz2020ArgumentMiningPipeline,
date = {2020},
title = {Towards an {{Argument Mining Pipeline Transforming Texts}} to {{Argument Graphs}}},
booktitle = {Computational {{Models}} of {{Argument}}},
author = {{Lenz}, {Mirko} and {Sahitaj}, {Premtim} and {Kallenberg}, {Sean} and {Coors}, {Christopher} and {Dumani}, {Lorik} and {Schenkel}, {Ralf} and {Bergmann}, {Ralph}},
series = {Frontiers in {{Artificial Intelligence}} {and} {{Applications}}},
abstract = {This paper tackles the automated extraction of components of argumentative information {and} their relations from natural language text. Moreover, we address a current lack of systems to provide a complete argumentative structure from arbitrary natural language text for general usage. We present an argument mining pipeline as a universally applicable approach for transforming German {and} English language texts to graph-based argument representations. We also introduce new methods for evaluating the performance based on existing benchmark argument structures. Our results show that the generated argument graphs can be beneficial to detect new connections between different statements of an argumentative text.},
eventtitle = {International {{Conference}} on {{Computational Models}} of {{Argument}}},
langid = {usenglish}
}
2019
A Systematic Comparison of Methods for Finding Good Premises for Claims
Lorik Dumani and Ralf Schenkel
Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'19, pp. 957-960, Association for Computing Machinery
Research on computational argumentation has recently become very popular. An argument consists of a claim that is supported or attacked by at least one premise. Its intention is the persuasion of others. An important problem in this field is retrieving good premises for a designated claim from a corpus of arguments. Given a claim, oftentimes existing approaches' first step is finding textually similar claims. In this paper we compare 196 methods systematically for determining similar claims by textual similarity, using a large corpus of (claim, premise) pairs crawled from debate portals. We also evaluate how well textual similarity of claims can predict relevance of the associated premises.
title = {A {{Systematic Comparison}} of {{Methods}} for {{Finding Good Premises}} for {{Claims}}},
booktitle = {Proceedings of the 42nd {{International ACM SIGIR Conference}} on {{Research}} {and} {{Development}} in {{Information Retrieval}}},
author = {{Dumani}, {Lorik} and {Schenkel}, {Ralf}},
series = {{{SIGIR}}'19},
pages = {957--960},
publisher = {Association for Computing Machinery},
location = {Paris, France},
doi = {10.1145/3331184.3331282},
url = {https://doi.org/10.1145/3331184.3331282},
urldate = {2020-08-22},
abstract = {Research on computational argumentation has recently become very popular. An argument consists of a claim that is supported or attacked by at least one premise. Its intention is the persuasion of others. An important problem in this field is retrieving good premises for a designated claim from a corpus of arguments. Given a claim, oftentimes existing approaches' first step is finding textually similar claims. In this paper we compare 196 methods systematically for determining similar claims by textual similarity, using a large corpus of (claim, premise) pairs crawled from debate portals. We also evaluate how well textual similarity of claims can predict relevance of the associated premises.},
isbn = {978-1-4503-6172-9}
}
Clustering of Argument Graphs Using Semantic Similarity Measures
Karsten Block, Simon Trumm, Premtim Sahitaj, Stefan Ollinger, and Ralph Bergmann
KI 2019: Advances in Artificial Intelligence, Vol. 11793, pp. 101-114, Springer International Publishing
Research on argumentation in Artificial Intelligence recently investigates new methods that contribute to the vision of developing robust argumentation machines. One line of research explores ways of reasoning with natural language arguments coming from information sources on the web as a foundation for the deliberation and synthesis of arguments in specific domains. This paper builds upon arguments represented as argument graphs in the standardized Argument Interchange Format. While previous work was focused on the development of semantic similarity measures used for the case-based retrieval of argument graphs, this paper addresses the problem of clustering argument graphs to explore structures that facilitate argumentation interpretation. We propose a k-medoid and an agglomerative clustering approach based on semantic similarity measures. We compare the clustering results based on a graph-based semantic measure that takes the structure of the argument into account with a semantic word2vec measure on the pure textual argument representation. Experiments based on the Microtext corpus show that the graph-based similarity is best on internal evaluation measures, while the pure textual measure performs very well for identifying topic-specific clusters.
BibTeX
@incollection{Block2019ClusteringArgumentGraphs,
date = {2019},
title = {Clustering of {{Argument Graphs Using Semantic Similarity Measures}}},
booktitle = {{{KI}} 2019: {{Advances}} in {{Artificial Intelligence}}},
author = {{Block}, {Karsten} and {Trumm}, {Simon} and {Sahitaj}, {Premtim} and {Ollinger}, {Stefan} and {Bergmann}, {Ralph}},
editor = {{Benzmüller}, {Christoph} and {Stuckenschmidt}, {Heiner}},
abstract = {Research on argumentation in Artificial Intelligence recently investigates new methods that contribute to the vision of developing robust argumentation machines. One line of research explores ways of reasoning with natural language arguments coming from information sources on the web as a foundation for the deliberation {and} synthesis of arguments in specific domains. This paper builds upon arguments represented as argument graphs in the standardized Argument Interchange Format. While previous work was focused on the development of semantic similarity measures used for the case-based retrieval of argument graphs, this paper addresses the problem of clustering argument graphs to explore structures that facilitate argumentation interpretation. We propose a k-medoid {and} an agglomerative clustering approach based on semantic similarity measures. We compare the clustering results based on a graph-based semantic measure that takes the structure of the argument into account with a semantic word2vec measure on the pure textual argument representation. Experiments based on the Microtext corpus show that the graph-based similarity is best on internal evaluation measures, while the pure textual measure performs very well for identifying topic-specific clusters.},
isbn = {978-3-030-30178-1 978-3-030-30179-8},
langid = {usenglish}
}
Good Premises Retrieval via a Two-Stage Argument Retrieval Model
Lorik Dumani
Proceedings of the 31st GI-Workshop Grundlagen von Datenbanken, CEUR Workshop Proceedings, Vol. 2367, pp. 3-8, CEUR
Argumentation is an important sub-field of Artificial Intelligence, which involves computational methods for reasoning and decision making based on argumentative structures. This paper contributes to case-based reasoning with argument graphs in the standardized Argument Interchange Format by improving the similarity-based retrieval phase. We explore a large range of novel approaches for semantic textual similarity measures (both supervised and unsupervised) and use them in the context of a graph-based similarity measure for argument graphs. In addition, the use of an ontology-based semantic similarity measure for argumentation schemes is investigated. With a range of experiments we demonstrate the strengths and weaknesses of the various methods and show that our methods can improve over our previous work. Our code is publicly available on GitHub.
BibTeX
@inproceedings{Lenz2019SemanticTextualSimilarity,
date = {2019},
title = {Semantic {{Textual Similarity Measures}} for {{Case-Based Retrieval}} of {{Argument Graphs}}},
author = {{Lenz}, {Mirko} and {Ollinger}, {Stefan} and {Sahitaj}, {Premtim} and {Bergmann}, {Ralph}},
editor = {{Bach}, {Kerstin} and {Marling}, {Cindy}},
series = {Lecture {{Notes}} in {{Computer Science}}},
volume = {11680},
pages = {219--234},
publisher = {Springer International Publishing},
location = {Otzenhausen, Germany},
doi = {10.1007/978-3-030-29249-2_15},
abstract = {Argumentation is an important sub-field of Artificial Intelligence, which involves computational methods for reasoning {and} decision making based on argumentative structures. This paper contributes to case-based reasoning with argument graphs in the standardized Argument Interchange Format by improving the similarity-based retrieval phase. We explore a large range of novel approaches for semantic textual similarity measures (both supervised {and} unsupervised) {and} use them in the context of a graph-based similarity measure for argument graphs. In addition, the use of an ontology-based semantic similarity measure for argumentation schemes is investigated. With a range of experiments we demonstrate the strengths {and} weaknesses of the various methods {and} show that our methods can improve over our previous work. Our code is publicly available on GitHub.},
eventtitle = {{{ICCBR}} 2019},
isbn = {978-3-030-29249-2},
langid = {usenglish}
}
Similarity Measures for Case-Based Retrieval of Natural Language Argument Graphs in Argumentation Machines
Ralph Bergmann, Mirko Lenz, Stefan Ollinger, and Maximilian Pfister
Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference, pp. 329-334, AAAI Press
In the field of argumentation, the vision of robust argumentation machines is investigated. They explore natural language arguments from information sources on the web and reason with them on the knowledge level to actively support the deliberation and synthesis of arguments for a particular user query. We aim at combining methods from case-based reasoning (CBR), information retrieval, and computational argumentation to contribute to the foundations of argumentation machines. In this paper, we focus on the retrieval phase of a CBR approach for an argumentation machine and propose similarity measures for arguments represented as argument graphs. We evaluate the similarity measures on a corpus of annotated micro texts and demonstrate the benefit of semantic similarity measures and the relevance of structural aspects.
abstract = {In the field of argumentation, the vision of robust argumentation machines is investigated. They explore natural language arguments from information sources on the web {and} reason with them on the knowledge level to actively support the deliberation {and} synthesis of arguments for a particular user query. We aim at combining methods from case-based reasoning (CBR), information retrieval, {and} computational argumentation to contribute to the foundations of argumentation machines. In this paper, we focus on the retrieval phase of a CBR approach for an argumentation machine {and} propose similarity measures for arguments represented as argument graphs. We evaluate the similarity measures on a corpus of annotated micro texts {and} demonstrate the benefit of semantic similarity measures {and} the relevance of structural aspects.},
eventtitle = {Thirty-{{Second International Florida Artificial Intelligence Research Society Conference}}}
}
2018
ReCAP - Information Retrieval and Case-Based Reasoning for Robust Deliberation and Synthesis of Arguments in the Political Discourse
Ralph Bergmann, Ralf Schenkel, Lorik Dumani, and Stefan Ollinger
Proceedings of the Conference "Lernen, Wissen, Daten, Analysen", CEUR Workshop Proceedings, Vol. 2191, pp. 49-60, CEUR
title = {{{ReCAP}} - {{Information Retrieval}} {and} {{Case-Based Reasoning}} for {{Robust Deliberation}} {and} {{Synthesis}} of {{Arguments}} in the {{Political Discourse}}},
booktitle = {Proceedings of the {{Conference}} "{{Lernen}}, {{Wissen}}, {{Daten}}, {{Analysen}}"},
author = {{Bergmann}, {Ralph} and {Schenkel}, {Ralf} and {Dumani}, {Lorik} and {Ollinger}, {Stefan}},
editor = {{Gemulla}, {Rainer} and {Ponzetto}, {Simone Paolo} and {Bizer}, {Christian} and {Keuper}, {Margret} and {Stuckenschmidt}, {Heiner}},
