Argument Mining Workshop 2022

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.

Call for Papers

ArgMining 2022 invites the submission of long and short papers on substantial, original, and unpublished research in all aspects of argument mining.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

Submission Information

Three types of papers can be submitted: Long papers (8 pages + references), short papers (4 pages + references), and demo papers (4 pages + references). Demo papers must include a URL to a running demo. Accepted papers will be given an additional page to account for the reviewers' comments. All papers will be treated equally in the workshop proceedings. The workshop follows ACL’s policies for submission, review, and citation. Moreover, authors are expected to adhere to the ethical code set out in the ACL Code of Ethics. Submissions that violate any of the policies will be rejected without review.

Please use the COLING 2022 style sheets for formatting your paper: https://coling2022.org/

Submission URL: https://www.softconf.com/coling2022/AM_2022

The workshop is running a double-blind review process. In preparing your manuscript, do not include any information which could reveal your identity, or that of your co-authors. The title section of your manuscript should not contain any author names, email addresses, or affiliation status. If you do include any author names on the title page, your submission will be automatically rejected. In the body of your submission, you should eliminate all direct references to your own previous work. That is, avoid phrases such as "this contribution generalizes our results for XYZ". Also, please do not disproportionately cite your own previous work. In other words, make your submission as anonymous as possible. We need your cooperation in our effort to maintain a fair, double-blind reviewing process - and to consider all submissions equally. Double Submission Papers that have been or will be submitted to other venues should indicate this at submission time. Upon acceptance at either event, the submission must be withdrawn from the other. To save reviewers' efforts, avoid submitting (or withdraw early) papers that are on track to be accepted elsewhere.

Important Dates

Submission due: !!! EXTENDED DEADLINE: July 18, 2022 !!!
Notification of acceptance: August 25, 2021
Camera-ready papers due: September 5, 2022

All deadlines are 11.59 pm UTC -12h (“anywhere on Earth”).

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.