Call for Papers

August 3-4 2017, Vancouver (Canada)
Co-located with ACL 2017
FINAL Call for Papers -- clarifications

Following several requests to the *SEM chairs, please find below the call for papers with some clarifications on the submission format, including style files and supplementary material (see submission instructions' section).

Due to this year's extremely tight conference schedule and the overlap of several conference and workshop deadlines, the deadline for submission to *SEM has been extended to April 17th.

*SEM is the yearly conference on lexical and computational semantics jointly organized by SIGLEX and SIGSEM, special interest groups of the ACL. *SEM brings together researchers interested in the semantics of natural languages and its computational modeling. The conference embraces symbolic and probabilistic approaches, and everything in between; theoretical contributions as well as practical applications are welcome in the form of long and short papers. 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.

Topics of interest include, but are not limited to:

- Representations of meaning (special topic this year: see below).
- Formal approaches to semantics.
- Lexical semantics.
- Distributional semantics; data-driven semantics; mathematical methods for semantics.
- Semantic parsing and interpretation; syntax-semantics interface.
- Textual inference; entailment and question answering.
- Frames and semantic role labeling.
- Semantic ambiguity and underspecification; word sense disambiguation and induction.
- Semantic annotation and evaluation.
- Temporal entities and relations; extraction of events and causal and temporal relations
- Entity linking; pronouns and coreference; single- and cross-document coreference
- Discourse semantics; discourse structure and presupposition; extra-propositional aspects of meaning; dialogue; semantics-pragmatics interface.
- Metaphor, irony, and figurative meaning; rhetorical relations.
- Multiword and idiomatic expressions.
- Generation and summarization.
- Knowledge mining and acquisition; semantic web and ontologies; ontology learning and population.
- Semantics in applications; semantics for social media; sentiment analysis.
- Grounding; semantics in multimodal approaches.
- Machine reading.


For the 2017 installment of *SEM, we especially welcome submissions on Representations of Meaning.

Over the years, computational semantics has developed many powerful representations of meaning, ranging from formal, extensional approaches, to vector-based models and structured lexical ontologies. The aims of these alternative approaches are diverse, some of them focusing on compositionality and the syntax-semantics interface, others on logical aspects of meaning, others yet on the relation between linguistic meaning and conceptual phenomena (including multimodal aspects). The produced representations have found their way into theoretical linguistic investigations as well as widespread applications such as the Semantic Web and the latest Artificial Intelligence research. This year, *SEM welcomes insights into what those different models contribute to a general theory of meaning and the broad aim of artificial language understanding. Are our semantic representations comparable? Combinable? What kind of applications or tasks do they support? What do our experimental results tell us about language? We solicit both theoretical and empirical contributions that will foster a discussion on the current state of research on semantic representations.


Papers submission due:       April 17, 2017
Notification of acceptance:  May 26, 2017
*SEM conference:             August 3-4, 2017

—all deadlines refer to 23:59pm UTC-11 (American Samoa time)


Katrin Erk, University of Texas at Austin
Yejin Choi,  University of Washington (joint invited speaker with SemEval 2017)


Submissions to *SEM-2017 must describe unpublished work and be written in English. We solicit both long and short papers.

Long papers may consist of up to eight (8) pages of content, plus any number of 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 may consist of up to four (4) pages, plus an unlimited number of 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.

Long papers typically describe a finished piece of original research. Short papers will typically describe ongoing research, project or system description, or an opinion piece.

As the reviewing will be 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) ...". Papers that do not conform to these requirements will be rejected without review. In addition, please do not post your submissions on the web until after the review process is complete. For a paper to be included in the conference proceedings, at least one of the authors must be registered as a participant at the *SEM conference.

Papers will be submitted using the START system at: submission of papers will need to be notified at submission: following ACL 2017 guidelines, papers that have been or will be submitted to other meetings or publications must indicate this at submission time in an author-blinded cover page.

Papers are to follow the ACL 2017 format: style files are provided at In line with the ACL guidelines, *SEM allows supplementary material to be added to the paper beyond the page limit. Note however that supplementary material should not be central to the paper and reviewers will not be required to take it into account. The space should be used to report preprocessing decisions, model parameters, and other details necessary for the replication of the experiments reported in the paper. It may also include explanations or details of proofs or derivations that do not fit into the paper, as well as lists of features or feature templates, sample inputs and outputs for a system, or pseudo-code. Supplementary material should go in an appendix after the references section, and be limited to a maximum of two pages.


General Chair:
    Nancy Ide, Vassar College

Program Chairs:
    Aurélie Herbelot, University of Trento
    Lluís Màrquez, Qatar Computing Research Institute

Publicity Chair:
    Eduardo Blanco, University of North Texas

Publication Chair:
    Sandro Pezzelle, University of Trento

See the complete list of Area Chairs at the conference website.


Contact email:
See the conference website,, for updated information.

(*SEM is pronounced "starsem")