The third UnImplicit workshop will be co-located with EACL 2024.
Workshop: March 21 or 22, 2024 (TBD on which of the two days)
EACL Conference: March 17-22, 2024
Website: https://unimplicit2024.github.io/
Paper submission: https://openreview.net/group?id=eacl.org/EACL/2024/Workshop/UnImplicit
* Paper submission deadline: December 18, 2023 *
* Paper submission deadline for papers with ARR Reviews: January 17, 2024 *
Implicitness, ambiguity, and underspecification are ubiquitous in language. Specifically, language utterances may contain ambiguities, such as the girl saw the man with the telescope; empty or fuzzy elements, such as the following: units of measurement, as in she is 30 or it costs 30 (30 what?); bridges and other missing links, as in she tried to enter the car, but the door was stuck (the door of what?); implicit semantic roles, as in I met her while driving (who was driving?); and various sorts of gradable phenomena, as in is a small elephant smaller than a big bee? Even though these phenomena may increase the chance of having misunderstandings, our conversational partners often manage to understand our utterances because they consider context-specific elements, such as time, culture, background knowledge and previous utterances in the conversation.
Despite the recent advancements on various semantic tasks, modeling implicitness and underspecification remains a challenging problem in NLP because the elements are not realized on the surface level. Instead of relying on superficial patterns, models are required to leverage contextual aspects of discourse that go beyond the sentence-level, for which there is a lack of available datasets or resources.
Past editions of this workshop have brought together a diverse group of NLP practitioners and theoreticians to address the challenges that implicit and underspecified language pose for NLP. The goal of the third edition of the workshop is to continue eliciting future progress on implicit and underspecified language with a strong focus on the annotation and development of aspects that go beyond the sentence level. Similar to past editions, we accept theoretical and practical contributions (long, short and non-archival) on all aspects related to the modeling (benchmarks, evaluation schemes, annotation, applications) of phenomena such as (but not restricted to): implicit arguments, fuzzy elements, zero anaphora, metonymy, and discourse markers.
In addition, we specifically encourage papers with a strong focus on the discourse, pragmatic and cognitive levels of language understanding with respect to implicit, ambiguous, and underspecified phenomena.
For reference, consider the program of the last two UnImplicit workshops: https://unimplicit.github.io/# and https://unimplicit2022.github.io
Important Dates
=============
Dec. 18, 2023: Workshop paper deadline (OpenReview)
Jan. 17, 2024: Deadline to commit papers with ARR Reviews (OpenReview)
Jan. 20, 2024: Notification of Acceptance
Jan. 30, 2024: Camera-ready papers due
Mar. 21-22, 2024: Workshop Dates (TBD on which of the two days)
All deadlines are 11.59 pm UTC -12h (“anywhere on Earth”).
Submissions
==========
We invite two types of submissions:
Archival: long (up to 8 pages) or short (up to 4 pages) papers, with unlimited references. These papers should report on complete, original and unpublished research and cannot be under submission elsewhere. If accepted, archival papers will appear in the workshop proceedings.
Non-archival: Extended abstracts (up to 2 pages) or copy of submission/publication, which can take two forms: Works in progress, that are not yet mature enough for a full submission. Or already published work, or work currently under submission elsewhere, which can be submitted in the form of the original abstract and a copy of the submission/publication.
We are not enforcing any anonymity period. The workshop will run its own review process, and papers can be submitted directly to OpenReview on Dec. 18th, 2023. It is also possible to submit a paper accompanied with reviews from the ACL Rolling Review system by Jan. 17th, 2024.
Both papers and extended abstracts must follow the EACL 2024 format.
Accepted papers and extended abstracts must be presented at the workshop and at least one author must be registered for the workshop.
Workshop organizers
==========
Valentina Pyatkin, AI2 and University of Washington
Elias Stengel-Eskin, UNC Chapel Hill
Alisa Liu, University of Washington
Sandro Pezzelle, University of Amsterdam
Daniel Fried, Carnegie Mellon University
Advisory committee
==========
Michael Roth, Stuttgart University
Reut Tsarfaty, Bar-Ilan University
Yoav Goldberg, Bar-Ilan University and AI2
Any questions regarding the workshop can be sent
to unimplicitworkshop [at] gmail.com.