First Call for Papers

Updates since the initial release on October 2:

The 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2021) is currently scheduled to take place in Mexico City, Mexico from June 6th to June 11th, 2021. We are monitoring the ongoing global pandemic and will update the conference plans (e.g. moving to a virtual or hybrid format) as needed closer to the conference dates.

NAACL-HLT 2021 aims to bring together researchers interested in the design and study of natural language processing technology as well as its applications to new problem areas. With this goal in mind, NAACL-HLT 2021 invites the submission of long and short papers on creative, substantial and unpublished research in all aspects of computational linguistics. More details will be available on the conference website.

NAACL-HLT 2021 has a goal of a diverse technical program–in addition to traditional research results, papers may present negative findings, survey an area, announce the creation of a new resource, argue a position, report novel linguistic insights derived using existing techniques, and reproduce, or fail to reproduce, previous results.

New in this Call for Papers

  • Announcing NAACL-HLT 2021 special theme
  • Updated topics list
  • Clarification: no separate industry track at NAACL-HLT 2021, industry track papers should be submitted to the main conference track, possibly to the NLP Applications area.
  • There will be an industry track with submission date after the main conference submission date (look out for industry track CFP).
  • Added detailed submission instructions, including ethics policy, reproducibility criteria, double submission policy, and sticky reviews.

Important Dates

Start of the anonymity period Friday October 23, 2020
Final paper submissions due
(long & short)
Monday November 23, 2020
Author Response Period Wednesday – Monday January 20 – 25, 2021
Notification of acceptance Wednesday March 10, 2021
Camera ready papers due Sunday April 11, 2021

All deadlines are 11.59 pm UTC -12h.

Topics

Relevant topics for the conference include, but are not limited to, the following areas (in alphabetical order):

  • Computational Social Science and Social Media
  • Dialogue and Interactive systems
  • Discourse and Pragmatics
  • Ethics, Bias, and Fairness
  • Green NLP
  • Language Generation
  • Information Extraction
  • Information Retrieval and Text Mining
  • Interpretability and Analysis of Models for NLP
  • Language Grounding to Vision, Robotics and Beyond
  • Language Resources and Evaluation
  • Linguistic Theories, Cognitive Modeling and Psycholinguistics
  • Machine Learning for NLP: Classification and Structured Prediction Models
  • Machine Learning for NLP: Language Modeling and Sequence to Sequence Models
  • Machine Translation
  • Multilinguality
  • NLP Applications
  • Phonology, Morphology and Word Segmentation
  • Question Answering
  • Semantics: Lexical Semantics
  • Semantics: Sentence-level Semantics and Textual Inference
  • Sentiment Analysis and Stylistic Analysis
  • Speech
  • Summarization
  • Syntax: Tagging, Chunking, and Parsing

For more detail regarding each area, please see the PC blog available (soon) on the conference website https://2021.naacl.org/.

NAACL-HLT 2021 Special Theme: New Challenges in NLP: Tasks, Methods, Positions

We have made significant progress in NLP over the last five years, and ACL 2020 had a special focus on taking stock of where we are as a field. For NAACL-HLT 2021, we invite you to think about the new problems and upcoming challenges our community should focus on next.

Despite the general applicability of the unsupervised pre-training/fine-tuning paradigm, many problems are still very challenging for current models. At the same time, given the recent progress, there are likely broad new classes of problems that can now be studied for the first time. What tasks or capabilities should we focus on next? What new classes of models should we be investigating? We envision papers falling into this theme including (but not limited to) (1) empirical and dataset papers that propose new challenges that bring us closer to human-level language understanding and generation, and (2) position papers framing an important direction or highlighting an understudied research problem.

Submission Types and Requirements

Following the previous conferences, NAACL-HLT 2021 will be open for two types of submissions: long and short papers. Author guidelines will be published at the conference webpage. Submission is electronic, using the Softconf START conference management for both long and short papers.

Long Papers

Long paper submissions must describe substantial, original, completed and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included.

Long paper submissions may consist of up to eight (8) pages of content, plus unlimited references; final camera-ready versions of accepted long papers will be given one additional page of content (up to 9 pages) so that reviewers’ comments can be taken into account.

Long papers will be presented orally or as posters as determined by the program committee. The decisions as to which papers will be presented orally and which as poster presentations will be based on nature rather than the quality of the work. There will be no distinction in the proceedings between long papers presented orally and those presented as posters.

Short Papers

Short paper submissions must describe original and unpublished work. Please note that a short paper is not a shortened long paper. Instead short papers should have a point that can be made in a few pages. Some kinds of short papers are:

  • A small, focused contribution
  • An interesting application nugget
  • A negative result
  • An opinion piece

Short paper submissions may consist of up to four (4) pages of content, plus unlimited 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.

Short papers will be presented in one or more oral or poster sessions. While short papers will be distinguished from long papers in the proceedings, there will be no distinction in the proceedings between short papers presented orally and as posters.

Author Guidelines

The ACL has released policies for submission, review and citation. Accompanying these are guidelines for authors. NAACL-HLT 2021 will adhere to these policies and guidelines. Submissions should:

Be relevant: Submissions to NAACL-HLT 2021 should be relevant to the audience.

Be original: The content of submissions to NAACL-HLT 2021 (the ideas, the findings, the results and the words) should be original; that is, should not have been published (or be accepted for publication) in another refereed, archival form (such as a book, a journal, or a conference proceedings). Authors are referred to the ACL author guidelines for additional information on what constitutes existing publication.

Authors may present preliminary versions of their work in other venues that are not refereed and/or not archival (e.g. course reports, theses, non-archival workshops, or on preprint servers such as arXiv.org). Authors should list all such previous presentations in the submission form. This will help the area chairs if questions of originality arise.

Double submission

No double submissions will be allowed for NAACL-HLT 2021. Authors submitting more than one paper to NAACL-HLT 2021 must ensure that the submissions do not overlap significantly (>25%) with each other. A given paper may only be submitted to a single NAACL-HLT 2021 track (Research, SRW or demos); any paper found to be submitted to more than one track will be rejected by all tracks. Resubmission to an appropriate workshop that follows the main conference is not affected by this policy.

Anonymity period

As mentioned above, the anonymity period for NAACL-HLT 2021 is from October 23, 2020 to March 10, 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.

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.

Clarifications:

  • The anonymity period starts at the end of Oct 23, 2020 anywhere on earth (11:59:59 pm UTC-12).

  • For papers submitted to arxiv or another pre-print server, there is often a delay between the submission time and the time the paper appears online. You will be in compliance with the anonymity rules as long as you submit by the end of Oct 23rd, even if the paper appears later (for arxiv papers, the submission time is seen under Submission history and the latest time to submit without violating the anonymity requirements is Oct 24, 2020 11:59:59 am UTC = Oct 23, 2020 11:59:59 pm UTC-12).

Double blind review

Double blind review is a form of peer review in which the identities of authors are not provided to reviewers, and the identities of reviewers are not provided to authors. To facilitate double blind review, submissions must not identify authors or their affiliations. For example, 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) …”.

Any preliminary non-archival versions of submitted papers should be listed in the submission form but not in the review version of the paper. NAACL-HLT 2021 reviewers are generally aware that authors may present preliminary versions of their work in other venues, but will not be provided the list of previous presentations from the submission form.

Authors are referred to the ACL author guidelines for additional information on how to facilitate double blind review.

Data management

If a submission describes work with a data set previously released by an organization or group (e.g. the LDC, ELRA, Kaggle), the source of the data should be appropriately referenced.

If a submission describes work with “found” data (e.g. data sampled from social media or the web), the source(s) of the data should be appropriately referenced, the method for sampling the data should be described, and any necessary permissions to use and/or release the data should be documented. In addition, the submission should document institutional review of the work as appropriate.

Human subjects

If a submission describes work involving human participants or personally identifiable information (including crowdsourced work), the submission should document institutional review of the work as well as informed consent and compensation procedures for participants, and anonymization procedures for the data.

Referencing prior work

Submissions should accurately reference prior and related work, including code and data. If a piece of prior work appeared in multiple venues, the version that appeared in a refereed, archival venue should be referenced. If multiple versions of a piece of prior work exist, the one used by the authors should be referenced. Authors should not rely on automated citation indices to provide accurate references for prior and related work.

Authors are referred to the ACL author guidelines for additional information on how to appropriately cite prior work.

Optional Supplementary Materials: Appendices, Software and Data

Each NAACL-HLT 2021 submission can be accompanied by one PDF appendix for the paper, one PDF for prior reviews and author response, one .tgz or .zip archive containing software, and one.tgz or .zip archive containing data. NAACL-HLT 2021 encourages the submission of these supplementary materials to improve the reproducibility of results, and to enable authors to provide additional information that does not fit in the paper. For example, anonymised related work (see above), preprocessing decisions, model parameters, feature templates, lengthy proofs or derivations, pseudocode, sample system inputs/outputs, and other details that are necessary for the exact replication of the work described in the paper can be put into the appendix.

However, the paper submissions need to remain fully self-contained, as these supplementary materials are completely optional, and reviewers are not even asked to review or download them. If the pseudo-code or derivations or model specifications are an important part of the contribution, or if they are important for the reviewers to assess the technical correctness of the work, they should be a part of the main paper, and not appear in the appendix. Supplementary materials must be fully anonymized to preserve the double-blind reviewing policy.

Ethics Policy

Authors are required to honour the ethical code set out in the ACM Code of Ethics. The consideration of the ethical impact of our research, use of data, and potential applications of our work has always been an important consideration, and as artificial intelligence is becoming more mainstream, these issues are increasingly pertinent. We ask that all authors read the code, and ensure that their work is conformant to this code. We reserve the right to reject papers on ethical grounds, where the authors are judged to have operated counter to the code of ethics, or have inadequately addressed legitimate ethical concerns with their work

Sticky Reviews (optional)

Authors resubmitting a paper that has been rejected from another venue are invited to submit alongside their paper the previous version of the paper, the reviews and an author response, following the procedure introduced at EMNLP last year. This is strictly optional. It is designed to mimic the revise-and-resubmit procedure underlying journals like TACL. We expect that the fact that a paper was rejected from another venue will not necessarily affect the paper’s decision in a negative way, but is likely to be beneficial to authors who believe they have addressed the problems identified, and can argue strongly for how the paper has been improved. The prior reviews will not be seen by reviewers, but be used as part of the NAACL-HLT 2021 decision process, primarily by area chairs and program chairs in review quality control, resolving disagreements between reviewers, and in deciding borderline papers.

Reproducibility Criteria

During the submission process, authors will be asked to answer the questions from the Reproducibility Checklist. The checklist is intended as a reminder to help the authors improve reproducibility of their papers. The papers are not required to meet all reproducibility criteria listed. However, the answers will be made available to the reviewers. Reviewers will be asked to assess the reproducibility of the work as part of their reviews. The updated checklist will be made available on the conference website, see previous versions in Dodge et al, 2019 and Joelle Pineau’s reproducibility checklist.

Style and formatting guidelines

Submissions should follow the NAACL-HLT 2021 style guidelines, which will be posted on the conference website. Long paper submissions must follow the two-column format of ACL proceedings without exceeding eight (8) pages of content. Short paper submissions must also follow the two-column format of ACL proceedings, and must not exceed four (4) pages. References do not count against these limits. We strongly recommend the use of the official NAACL-HLT 2021 style templates, available (soon) on the conference website. All submissions must be in PDF format. Submissions that do not adhere to the above author guidelines or ACL policies will be rejected without review.

Presentation Requirement

All accepted papers must be presented at the conference to appear in the proceedings. At least one author of each accepted paper must register for NAACL-HLT 2021 by the early registration deadline.

Contact Information

Email: naacl-2021-program-chairs@googlegroups.com

Program co-chairs:

  • Anna Rumshisky (University of Massachusetts Lowell)
  • Luke Zettlemoyer (University of Washington & Facebook)
  • Dilek Hakkani-Tur (Amazon Alexa AI)

General chair: Kristina Toutanova (Google)