Call for Papers

*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 include, but are not limited to:

  • Lexical semantics and word representations

  • Compositional semantics and sentence representations

  • Statistical, machine learning and deep learning methods for semantics

  • Multilingual and cross-lingual semantics

  • Word sense disambiguation and induction

  • Semantic parsing; syntax-semantics interface

  • Frame semantics and semantic role labeling

  • Textual inference, entailment and question answering

  • Formal approaches to semantics

  • Extraction of events and 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

  • 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:

https://folk.idi.ntnu.no/odderik/reproducibility_guidelines_how_to.html

https://folk.idi.ntnu.no/odderik/reproducibility_guidelines.pdf


Submission instructions

Submission is electronic, using the Softconf START conference management system. The submission site is now available.

Submissions to STARSEM 2021 should follow this year's ACL style, as detailed here. Submissions must describe unpublished work and be written in English.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. 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.

As the reviewing will be double-blind, the paper must not include the authors' names and affiliations. Furthermore, self-references that reveal the author's identity, e.g., "We previously showed (Smith, 1991) ..." must be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ...". As for online paper sharing, at STARSEM, we adopt the ACL policy for submission, which can be found here. Papers that do not conform to requirements will be rejected without review. For a paper to be included in the conference proceedings, at least one of the authors must be registered as a participant at the STARSEM conference.


Anonymity period

To protect the integrity of double-blind review and ensure that submissions are reviewed fairly, we adopt the rules and guidelines for ACL conferences. The following rules and guidelines make reference to the anonymity period, which runs from 1 month before the submission deadline (starting March 9, 2021 11:59PM UTC-12:00) up to the date when your paper is either accepted, rejected, or withdrawn (May 28, 2021).

  • You may not make a non-anonymized version of your paper available online to the general community (for example, via a preprint server) during the anonymity period. By a version of a paper we understand another paper having essentially the same scientific content but possibly differing in minor details (including title and structure) and/or in length (e.g., an abstract is a version of the paper that it summarizes).

  • If you have posted a non-anonymized version of your paper online before the start of the anonymity period, you may submit an anonymized version to the conference. The submitted version must not refer to the non-anonymized version, and you must inform the program chair(s) that a non-anonymized version exists.

  • You may not update the non-anonymized version during the anonymity period, and we ask you not to advertise it on social media or take other actions that would further compromise double-blind reviewing during the anonymity period.

  • Note that, while you are not prohibited from making a non-anonymous version available online before the start of the anonymity period, this does make double-blind reviewing more difficult to maintain, and we therefore encourage you to wait until the end of the anonymity period if possible. Alternatively, you may consider submitting your work to the Computational Linguistics journal, which does not require anonymization and has a track for “short” (i.e., conference-length) papers.