5th Workshop on Argument Mining

EMNLP 2018



The workshop will be collocated with EMNLP 2018 in Brussels. The workshops will be held on November 1.

About the Workshop

Argument mining (also, “argumentation mining”) is a relatively new research field within the rapidly evolving area of Computational Argumentation. The tasks pursued within this field are highly challenging with many important practical applications. These include automatically identifying argumentative structures within discourse, e.g., premises, conclusion, and argumentation scheme of each argument, as well as relationships between pairs of arguments and their components. To date, researchers have investigated a plethora of methods to address these tasks in various areas, including legal documents, user generated Web discourse, on-line debates, product reviews, academic literature, newspaper articles, dialogical domains, and Wikipedia articles. Relevant manually annotated corpora are released at an increasing pace, further enhancing the research in the field. In addition, argument mining is inherently tied to sentiment analysis, since an argument frequently carries a clear sentiment towards its topic. Correspondingly, this year’s workshop will be coordinated with the corresponding WASSA workshop, aiming to have a joint poster session.

Argument mining can give rise to various applications of great practical importance. For instance, by developing methods that can extract and visualize the main pro and con arguments raised in a collection of documents towards a query of interest, one can enhance data-driven decision making. In instructional contexts, argumentation is a pedagogically important tool for conveying and assessing the students' command of course material, as well as for advancing critical thinking. Written and diagrammed arguments by students represent educational data that can be mined for purposes of assessment and instruction. This is especially important given the wide-spread adoption of computer-supported peer review, computerized essay grading, and large-scale online courses and MOOCs. Additionally, mining pros and cons may be useful in multiple business applications, for instance, for researching a company or considering the potential of a possible investment.

Success in argument mining requires interdisciplinary approaches informed by natural language processing technology, artificial intelligence approaches, theories of semantics, pragmatics and discourse, knowledge of discourse of domains such as law and science, argumentation theory, computational models of argumentation, and cognitive psychology. The goal of this workshop is to provide a follow-on forum to the last four years’ Argument Mining workshops at ACL and EMNLP, the major research forum devoted to argument mining in all domains of discourse.

Important Dates

  • Submission due: July 12, 2018 July 17, 2018
  • Author Notification: August 18, 2018
  • Camera Ready: August 31, 2018
  • Workshop Date: November 1, 2018
  • Submission link: https://www.softconf.com/emnlp2018/argmining2018
  • Note: All deadlines are calculated at 11:59pm Pacific Daylight Savings Time (UTC -7h).


09:00 - 09:10 Openings

Session 1:

09:10 - 10:10Keynote Talk
Argumentation and Human Reason
Hugo Mercier
10:10 - 10:30 Argumentative Link Prediction using Residual Networks and Multi-Objective Learning
Andrea Galassi, Marco Lippi and Paolo Torroni
10:30 - 11:00Coffee Break

Session 2:

11:00 - 11:20 End-to-End Argument Mining for Discussion Threads Based on Parallel Constrained Pointer Architecture
Gaku Morio and Katsuhide Fujita
11:20 - 11:40 ArguminSci: A Tool for Analyzing Argumentation and Rhetorical Aspects in Scientific Writing
Anne Lauscher, Goran Glavaš and Kai Eckert
11:40 - 12:00 Evidence Type Classification in Randomized Controlled Trials
Tobias Mayer, Elena Cabrio and Serena Villata
12:00 - 12:20 Predicting the Usefulness of Amazon Reviews Using Off-The-Shelf Argumentation Mining
Marco Passon, Marco Lippi, Giuseppe Serra and Carlo Tasso

12:20 - 14:30

Lunch and Poster Presentations
A walking lunch will be served during the session - sponsored by IBM

Session 3:

14:30 - 14:50 Dave the debater: a retrieval-based and generative argumentative dialogue agent
Dieu-Thu Le, Cam Tu Nguyen and Kim Anh Nguyen
14:50 - 15:30Special Presentation
Project Debater
Noam Slonim and Ranit Aharonov
15:30 - 16:00Coffee Break

Session 4:

16:00 - 16:20 PD3: Better Low-Resource Cross-Lingual Transfer By Combining Direct Transfer and Annotation Projection
Steffen Eger, Andreas Rücklé and Iryna Gurevych
16:20 - 16:40 Cross-Lingual Argumentative Relation Identification: from English to Portuguese
Gil Rocha, Christian Stab, Henrique Lopes Cardoso and Iryna Gurevych
16:40 - 17:00 More or less controlled elicitation of argumentative text: Enlarging a microtext corpus via crowdsourcing
Maria Skeppstedt, Andreas Peldszus and Manfred Stede
17:00 - 17:30Best paper announcement and closing