2020Q3 Reports: SIGLEX

The following SIGLEX Executive Board officers are serving until Spring 2022:

President

- Preslav Nakov, Qatar Computing Research Institute, HBKU, Qatar

Secretary

- Aline Villavicencio, The University of Sheffield, UK

Executive Board

- Vice-President Elect: Steven Bethard, The University of Arizona, USA

- Vice-Secretary Elect: Ekaterina Shutova, University of Amsterdam, The Netherlands

SIGLEX Section Representatives on the Executive Board

- MWE section: Carlos Ramisch, Aix Marseille University, France

- SemEval section: David Jurgens, University of Michigan, Ann Arbor, USA

We currently have 852 members and we manage membership and mailing lists using the website that was developed by Ken Litkowski and is now managed by Preslav Nakov.

SIGLEX has two sections:

Multiword Expressions (MWE) with 205 members. SemEval with 982 members.

SIGLEX (co-)organises three yearly events: SemEval, *SEM, and MWE:

*SEM 2020

The 9th Joint Conference on Lexical and Computational Semantics (* SEM 2020), organized by SIGLEX, will be co-located with COLING-2020 in Barcelona, Spain in December 2020.

General Chair

- Iryna Gurevych, Technische Universität Darmstadt

Program Chairs

- Marianna Apidianaki, University of Helsinki

- Manaal Faruqui, Google Assistant

Publication Chair

- Jonathan May, ISI, University of Southern California

Area Chairs

Lexical semantics and word representations

- Mohammad Taher Pilehvar (Iran University of Science and Technology)

- Vered Shwartz (Allen Institute for Artificial Intelligence (AI2) & University of Washington)

Semantic composition and sentence representations

- Ivan Vulić (University of Cambridge)

- Germán Kruszewski (Facebook AI Research)

Discourse, dialogue, and generation

- Junyi Jessy Li (University of Texas at Austin)

- Philippe Muller (Université Paul Sabatier, IRIT)

Multilinguality

- Alessandro Raganato (University of Helsinki)

- Shyam Upadhyay (Google Assistant)

Psycholinguistics and semantic processing

- Harm Brouwer (Saarland University)

- Alessandra Zarcone (Fraunhofer IIS)

Resources and evaluation

- Darja Fišer (University of Ljubljana)

- Goran Glavaš (University of Mannheim)

Theoretical and formal semantics

- Stergios Chatzikyriakidis (University of Gothenburg)

- Denis Paperno (Utrecht University)

Commonsense reasoning and natural language understanding

- Ellie Pavlick (Brown University)

- Rachel Rudinger (University of Maryland)

Sentiment analysis and argument mining

- Saif Mohammad (National Research Council Canada)

- Elena Cabrio (Université Côte d'Azur, INRIA, CNRS)

SemEval 2020

The International Workshop on Semantic Evaluation (SemEval 2020), organized by SIGLEX, will be co-located with COLING-2020 in Barcelona, Spain in December 2020.

Organizers:

- Aurelie Herbelot, University of Trento

- Xiaodan Zhu, Queen's University

- Nathan Schneider, Georgetown University

- Alexis Palmer, University of North Texas

- Jonathan May, ISI, University of Southern California

- Ekaterina Shutova, University of Amsterdam

SemEval 2020 included the following 12 shared tasks organized in four tracks:

Lexical semantics

- Task 1: Unsupervised Lexical Semantic Change Detection

- Task 2: Predicting Multilingual and Cross-Lingual (Graded)

- Task 3: Graded Word Similarity in Context (GWSC)

Common Sense Knowledge and Reasoning, Knowledge Extraction

- Task 4: Commonsense Validation and Explanation

- Task 5: Modelling Causal Reasoning in Language: Detecting Counterfactuals

- Task 6: DeftEval: Extracting Definitions from Free Text in Textbooks

Humour, Emphasis, and Sentiment

- Task 7: Assessing Humor in Edited News Headlines

- Task 8: Memotion Analysis

- Task 9: Sentiment Analysis for Code-Mixed Social Media Text

- Task 10: Emphasis Selection for Written Text in Visual Media

Societal Applications of NLP

- Task 11: Detection of Propaganda Techniques in News Articles

- Task 12: OffensEval 2: Multilingual Offensive Language Identification in Social Media

The proceedings contain both Task Description papers that describe each of the above tasks, and System Description papers that present the systems that participated in these tasks. A total of 12 task description papers and about 300 system description papers are included in the proceedings.

SemEval 2021

32 task proposals were received and reviewed by 68 external reviewers from the ACL community. 12 of the tasks were selected for SemEval 2020. For more details about the event, check out http://alt.qcri.org/semeval2020/

MWE-LEX 2020

Program Committee Chairs

Research track, MWE-specific topics:

- Stella Markantonatou, Institute for Language and Speech Processing, R.C. "Athena" (Greece)

- Jelena Mitrović, University of Passau (Germany)

Research track, MWE-LEX topics:

- John McCrae, National University of Ireland Galway (Ireland)

- Carole Tiberius, Dutch Language Institute in Leiden (Netherlands)

Shared task track:

- Carlos Ramisch, Aix Marseille University (France)

- Ashwini Vaidya, Indian Institute of Technology in Delhi (India)

The 15th edition of the yearly flagship event of the MWE Section, called Workshop on Multiword Expressions (MWE), was co-located with the ACL 2019 conference in Florence, Italy. In a quest for synergies with related communities, the Section joined forces with the Global Wordnet Association (GWA). Thus, the event was called Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019).

Invited talk: "When the whole is greater than the sum of its parts: Multiword expressions and idiomaticity", by Aline Villavicencio, University of Essex (UK) and Federal University of Rio Grande do Sul (Brazil)

Submissions: 37 papers (20 long and 17 short) were submitted. 12 long papers and 8 short ones were selected. 6 papers (1 short and 5 long) were selected as oral presentations and 14 (7 short and 7 long) as posters. The overall acceptance rate was 54%.

Community discussion: it will include feedback from this joint event, MWE-related announcements, announcements about the SIGLEX-MWE Steering Committee recruitment, plans for future shared task editions and for collaboration between the Universal Dependencies and the PARSEME communities.