The 10th Workshop on Argument Mining

December 7, 2023 - HYBRID format

Co-located with EMNLP 2023 in Singapore

ArgMining 2023 is over. Thanks to everyone for participating!

Argument mining (also known as "argumentation mining") is a gradually maturing research area within computational linguistics. At its heart, argument mining involves the automatic identification of argumentative structures in free text, such as the conclusions, premises, and inference schemes of arguments as well as their interrelations and counter-considerations. To date, researchers have investigated argument mining on genres such as legal documents, product reviews, news articles, online debates, user-generated web discourse, Wikipedia articles, scholarly data, persuasive essays, tweets, and dialogues. Aside from mining argumentative components, the field focuses on studying argument quality assessment, argument persuasiveness, and the synthesis of argumentative texts.

Argument mining gives rise to various practical applications of great importance. In particular, it provides methods that can find and visualize the main pro and con arguments in a text corpus --- or even in an argument search on the web --- towards a topic or query of interest. In instructional contexts, written and diagrammed arguments represent educational data that can be mined for conveying and assessing students' command of course material. Moreover, debate technologies like IBM Project Debater that drew a lot of attention recently rely heavily on argument mining tasks.

While solutions to basic tasks such as component segmentation and classification slowly become mature, many tasks remain largely unsolved, particularly in more open genres and topical domains. Success in argument mining requires interdisciplinary approaches informed by NLP technology, theories of semantics, pragmatics and discourse, knowledge of discourse in application domains, artificial intelligence, information retrieval, argumentation theory, and computational models of argumentation.


09:00–09:10 Opening Remarks

09:10–10:10 Panel Session

10:10–10:34 Paper Session I

  • Dimensionality Reduction for Machine Learning-based Argument Mining (Andrés Segura-Tinoco and Iván Cantador)
  • Argument Detection in Student Essays under Resource Constraints (Omid Kashefi, Sophia Chan and Swapna Somasundaran)

10:34–11:00 Break

11:00–12:30 Paper Session II

  • On the Impact of Reconstruction and Context for Argument Prediction in Natural Debate (Zlata Kikteva, Alexander Trautsch, Patrick Katzer, Mirko Oest, Steffen Herbold and Annette Hautli-Janisz)
  • Unsupervised argument reframing with a counterfactual-based approach (Philipp Heinisch, Dimitry Mindlin and Philipp Cimiano)
  • Legal Argument Extraction from Court Judgements using Integer Linear Programming (Basit Ali, Sachin Pawar, Girish Palshikar, Anindita Sinha Banerjee and Dhirendra Singh)
  • Teach Me How to Argue: A Survey on NLP Feedback Systems in Argumentation (Camelia Guerraoui, Paul Reisert, Naoya Inoue, Farjana Sultana Mim, Keshav Singh, Jungmin Choi, Irfan Robbani, Shoichi Naito, Wenzhi Wang and Kentaro Inui)
  • Detecting Argumentative Fallacies in the Wild: Problems and Limitations of Large Language Models (Ramon Ruiz-Dolz and John Lawrence)
  • Constituency Tree Representation for Argument Unit Recognition (Samuel Guilluy, Florian Mehats and Billal Chouli)
  • Mind the Gap: Automated Corpus Creation for Enthymeme Detection and Reconstruction in Learner Arguments [Findings] (Maja Stahl, Nick Düsterhus, Mei-Hua Chen and Henning Wachsmuth)
  • Automatic Analysis of Substantiation in Scientific Peer Reviews [Findings] (Yanzhu Guo, Guokan Shang, Virgile Rennard, Michalis Vazirgiannis and Chloé Clavel)

12:30–14:00 Lunch

14:00–15:00 Shared Task Session

  • 14:00–14:30 ImageArg-Shared-Task-2023: The First Shared Task in Multimodal Argument Mining (Zhexiong Liu, Mohamed Elaraby, Yang Zhong and Diane Litman)
  • 14:30–15:00 PragTag-2023: The First Shared Task on Pragmatic Tagging of Peer Reviews (Nils Dycke, Ilia Kuznetsov and Iryna Gurevych)

15:00–16:00 Poster Session

  • Shared Task Papers
  • Main Workshop Papers

15:30–16:00 Break

16:00–17:00 Keynote Speech

17:00–17:52 Paper Session III

  • Towards Fine-Grained Argumentation Strategy Analysis in Persuasive Essays (Robin Schaefer, René Knaebel and Manfred Stede)
  • Using Fill-Mask Language Model Probabilities of Connectives for Stance Detection in English Discourse (Regina Stodden, Laura Kallmeyer, Lea Kawaletz and Heidrun Dorgeloh)
  • Stance-Aware Re-Ranking for Non-factual Comparative Queries (Jan Heinrich Reimer, Alexander Bondarenko, Maik Fröbe and Matthias Hagen)
  • Unveiling the Power of Argument Arrangement in Online Persuasive Discussions [Findings] (Nailia Mirzakhmedova, Johannes Kiesel, Khalid Al Khatib and Benno Stein)
  • High-quality argumentative information in low resources approaches improves counter-narrative generation [Findings] (Damián Furman, Pablo Torres, José Rodríguez, Diego Letzen, Maria Vanina Martinez and Laura Alonso Alemany)

18:00–18:15 Closing Remarks + Best Paper Award

Panel Session

In celebration of the 10th anniversary of the workshop series, we will host a panel session to reflect on the past and future of argument mining with the following renowned researchers in the field:

Keynote Speaker

Noam Slonim

Title: "Project Debater and argument mining - a historical and somewhat personal perspective"

Noam Slonim

IBM Research AI; founder and Principal Investigator of Project Debater

Best Paper Award

Best Paper

Unsupervised argument reframing with a counterfactual-based approach (Philipp Heinisch, Dimitry Mindlin and Philipp Cimiano)

Best Paper Nominations

Shared Tasks

We are pleased to present two shared tasks as part of ArgMining 2023:

ImageArg-Shared-Task-2023: The First Shared Task in Multimodal Argument Mining

Task Description:

There has been a recent surge of interest in developing methods and corpora to improve and evaluate persuasiveness in natural language applications. However, these efforts have mainly focused on the textual modality, neglecting the influence of other modalities. To address this limitation, we introduced a new multimodal dataset called ImageArg. This dataset includes persuasive tweets along with associated images, aiming to identify the image's stance towards the tweet and determine its image persuasiveness concerning a specific topic. To further this goal, we designed two shared tasks.

Participants can choose Task A or Task B, or both.

Task A (Multimodal Argument Stance Classification)
Given a tweet composed of a text and image, predict whether the given tweet Supports or Opposes the given topic.

Task B (Multimodal Image Persuasiveness Classification)
Given a tweet composed of text and image, predict whether the image makes the tweet text more Persuasive or Not.

Task Organizers:

Zheixong Liu, Mohamed Elaraby, Yang Zhong, Diane Litman (University of Pittsburgh)

PragTag-2023: The First Shared Task on Pragmatic Tagging of Peer Reviews

Task Description:

Peer reviews are argumentative texts that discuss the strengths and weaknesses of the paper under-review and provide suggestions for improvement. The automatic analysis of intentions in reviewer argumentation has numerous applications, from the analysis of reviewing practices, to aggregating information from multiple reviews and assisting junior reviewers. However, reviewing practices vary across fields and peer reviewing data for training is scarce; this introduces the danger of performance shift of such automatic analysis across disciplines. With this shared task, we invite the community to explore these challenges, using recently introduced multi-domain corpora of peer reviews.

Task Organizers:

Ilia Kuznetsov, Nils Dycke (Technical University of Darmstadt, UKP Lab)


Organizing Committee

Program Committee

  • Rodrigo Agerri, University of the Basque Country
  • Yamen Ajjour, Leibniz Universität Hannover
  • Khalid Al Khatib, University of Groningen
  • Tariq Alhindi, Columbia University
  • Emily Allaway, Columbia University
  • Safi Eldeen Alzi'abi, Isra University
  • Özkan Aslan, Afyon Kocatepe University
  • Roy Bar-Haim, IBM Research AI
  • Miriam Butt, University of Konstanz
  • Elena Cabrio, CNRS, Inria, I3S
  • Claire Cardie, Cornell University
  • Jonathan Clayton, University of Sheffield
  • Johannes Daxenberger, summetix
  • Lorik Dumani, Trier University
  • Roxanne El Baff, German Aerospace Center (DLR)
  • Ivan Habernal, Technische Universität Darmstadt
  • Shohreh Haddadan, University of Luxembourg
  • Yufang Hou, IBM Research AI
  • Xinyu Hua, Bloomberg AI
  • Lea Kawaletz, HHU Düsseldorf
  • Christopher Klamm, University of Mannheim
  • Gabriella Lapesa, University of Stuttgart
  • John Lawrence, University of Dundee
  • Beishui Liao, Zhejiang University
  • Simon Parsons, University of Lincoln
  • Georgios Petasis, NCSR Demokritos, Athens
  • Olesya Razuvayevskaya, University of Sheffield
  • Chris Reed, University of Dundee
  • Patrick Saint-Dizier, IRIT, CNRS
  • Robin Schaefer, University of Potsdam
  • Jodi Schneider, University of Illinois Urbana-Champaign
  • Gabriella Skitalinskaya, Leibniz Universität Hannover
  • Manfred Stede, University of Potsdam
  • Benno Stein, Bauhaus-Universität Weimar
  • Simone Teufel, University of Cambridge
  • Serena Villata, Université de Nice
  • Henning Wachsmuth, Leibniz Universität Hannover
  • Vern R. Walker, Hofstra University
  • Timon Ziegenbein, Leibniz Universität Hannover

Past Workshops


We abide by the ACL anti-harassment policy.