*SEM brings together researchers interested in the semantics of (many and diverse!) natural languages and its computational modeling. The conference embraces data-driven, neural, and probabilistic approaches, as well as symbolic approaches and everything in between; practical applications as well as theoretical contributions are welcome. The long-term goal of *SEM is to provide a stable forum for the growing number of NLP researchers working on all aspects of semantics of (many and diverse!) natural languages.
Topics of interest
• Lexical semantics and word representations
• Compositional semantics and sentence representations
• Statistical, machine learning, and deep learning methods in semantic tasks
• Multilingual and cross-lingual semantics
• Word sense disambiguation and induction
• Semantic parsing, and syntax-semantics interface
• Frame semantics and semantic role labeling
• Textual inference, textual entailment, and question answering
• Formal approaches to semantics
• Extraction of events and of causal and temporal relations
• Entity linking, pronouns and coreference
• Discourse, pragmatics, and dialogue
• Machine reading
• Extra-propositional aspects of meaning
• Multiword and idiomatic expressions
• Metaphor, irony, and humor
• Knowledge mining and acquisition
• Common sense reasoning
• Language generation
• Semantics in NLP applications: sentiment analysis, abusive language detection, summarization, fact-checking, etc.
• Multidisciplinary research on semantics
• Grounding and multimodal semantics
• Psycholinguistcs
• Interpretability and Explainability
• Human semantic processing
• Semantic annotation, evaluation, and resources
• Ethical aspects and bias in semantic representations
We encourage authors to think about the ethical aspects of their work, and to address and discuss all ethical questions and implications relevant to their research. STARSEM values reproducibility and particularly welcomes submissions that adhere to the reproducibility guidelines as specified here.
Submission Instructions
Submissions must describe unpublished work and be written in English. We solicit both long and short papers. Please note that double submission of papers will need to be notified at submission.
Long papers describe original research and may consist of up to eight (8) pages of content, plus unlimited pages for references. Appendices are allowed after the references, but the paper should be self-contained and reviewers will not be required to check the appendices, if any. Final versions of long papers will be given one additional page of content (up to 9 pages) so that reviewers’ comments can be taken into account. Short papers describe original focused research and may consist of up to four (4) pages, plus unlimited pages for references. Upon acceptance, short papers will be given five (5) content pages in the proceedings. Authors are encouraged to use this additional page to address reviewers comments in their final versions.
Submissions should follow the ARR formatting requirements. The deadline for direct submissions is Feb 22, 2024, and these submissions will be reviewed by the *SEM-2024 program committee. ACL Rolling Review (ARR) submissions can be committed to *SEM up to March 22, 2024 (authors of ARR-reviewed papers need to include their OpenReview link with reviews in the submission form). Both types of submissions are through OpenReview. Limitations and Ethics Statement sections are allowed and encouraged, but they are not mandatory. They should be placed after the conclusion and they will not count towards the overall page limit.). In *SEM there is no special policy against multiple submissions, but this should be notified to the Program Chairs.
Submission link: https://openreview.net/group?id=aclweb.org/StarSEM/2024/Conference
Important Dates
Direct submission deadline: Feb 22, 2024
ARR-reviewed paper submission deadline: Mar 22, 2024
Notification of acceptance: Apr 22, 2024
Camera-ready deadline: May 5, 2024
Conference date: Jun 16, 2024
Anonymity period
*SEM 2024 will follow the new anonymity policy adopted by ACL and described here. In short, papers can be published in arxiv or other preprint servers, but extensive promotion while in the review process is discouraged.
General Chair
Jose Camacho-Collados (Cardiff University)
Program Chairs
Danushka Bollegala (Amazon, University of Liverpool)
Vered Shwartz (University of British Columbia, Vector Institute)