The 9th Workshop on Argument Mining

Virtual: Join the workshop through Underline. A Zoom link is available in the linked page.

On-site: Room 103

Argument mining (also known as "argumentation mining") is a growing 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 pro- and con-relations. To date, researchers have investigated argument mining on many genres, such as legal documents, product reviews, news articles, online debates, Wikipedia articles, essays, academic literature, tweets, and dialogues. In addition, argument quality assessment and generation are also important problems. 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 written text and dialogue and that enable argument search on the web for a topic of interest. In educational contexts, argument mining can be applied to written and diagrammed arguments for instructing and assessing students' critical thinking. In information retrieval, argument mining is expected to play a salient role in the emerging field of conversational search.

We are looking for diverse research work on argument mining in real-world applications from various domains. Real-world applications include argument analysis in education, finance, law, public policy, and other social sciences, argument web search, opinion analysis in customer reviews, argument analysis in meetings, and scientific writing.

Program

Panel Session

We will be hosting a panel session with the following domain experts

Legal

Laura Alonso Alemany

Finance

Chung-Chi Chen

Education

Beata Beigman Klebanov

E-governance

Joonsuk Park

Business

Michael Yeomans

Keynote Speaker

Title: Mining for Persuasive Ingredients: What’s the Right Mix?

Prof. Dr. Hans Hoeken

Department of Languages, Literature, and Communication, Utrecht University

Best paper award

• Winner: ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining (Zhexiong Liu, Meiqi Guo, Yue Dai, Diane Litman)
• Runner-up: Data Augmentation for Improving the Prediction of Validity and Novelty of Argumentative Conclusions (Philipp Heinisch, Moritz Plenz, Juri Opitz, Anette Frank, Philipp Cimiano)
• Runner-up: Analyzing Culture-Specific Argument Structures in Learner Essays (Wei-Fan Chen, Mei-Hua Chen, Garima Mudgal, Henning Wachsmuth)
• Runner-up: Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweets (Amelie Wuhrl, Roman Klinger)

Shared Task: Predicting the validity and novelty of arguments

Webpage: https://phhei.github.io/ArgsValidNovel/

Organized by Philipp Heinisch, Philipp Cimiano (University of Bielefeld), Anette Frank, and Juri Opitz (University of Heidelberg)

In recent years, there have been increased interests in understanding how to assess the quality of arguments systematically. To foster more research on this topic in the community, we plan to organize a task consisting of assessing whether computational models can reliably assess the validity and novelty of a conclusion given a set of the textual premises.

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

• Task A: The first task consists of a binary classification task along the dimensions of novelty and validity, classifying a conclusion as being valid/novel or not given a textual premise.
• Task B: The second subtask will consist in comparing two conclusions in terms of validity / novelty.

Call for Papers (Closed)

ArgMining 2022 invites the submission of long and short papers on substantial, original, and unpublished research in all aspects of argument mining. The workshop solicits LONG and SHORT papers for oral and poster presentations, as well as DEMOS of argument/argumentation mining systems and tools.

The topics for submissions include but are not limited to:

• Automatic identification of argument components (premises and conclusions or more fine-grained), and relations between arguments and counterarguments (support and attack or more fine-grained) within/across documents
• Automatic assessment of properties of arguments and argumentation, such as argumentation schemes, stance, quality, and persuasiveness
• Automatic synthesis of arguments and their components, including the consideration of discourse goals (e.g., stages of a critical discussion or rhetorical strategies) and the possibly needed preceding analyses
• Creation and evaluation of argument annotation schemes, relationships to linguistic and discourse annotations, (semi-) automatic argument annotation methods and tools, and creation of argumentation corpora
• Management of spoken and transcribed dialogue, argument mining from such data, including additional challenges posed by real-time processing
• Combination of NLP methods and AI models developed for argumentation, such as abstract and structured argumentation frameworks
• Combination of information retrieval methods with argument mining, e.g. in order to build the next generation of argumentative (web) search engines
• Use of argument mining for studying research questions from education, finance, law, public policy, digital humanities, and any other social sciences
• Reflection on the ethical aspects and societal impact of argument mining methods

Scholarships

Committee

Organizing Committee

Gabriella Lapesa

Jodi Schneider

Yohan Jo

Sougata Saha

Program Committee

Best Paper Committee

Local Chair

Past Workshops

Policy

We abide by the ACL anti-harassment policy.

Sponsors