Adapt-NLP 2021

April 20, 2021, EACL, Kyiv

Call For Papers

Overview

The growth in computational power and the rise of Deep Neural Networks (DNNs) have revolutionized the field of Natural Language Processing (NLP). The ability to collect massive datasets with the capacity to train big models on powerful GPUs, has yielded NLP-based technology that was beyond imagination only a few years ago.

Unfortunately, this technology is still limited to a handful of resource rich languages and domains. This is because most NLP algorithms rely on the fundamental assumption that the training and the test sets are drawn from the same underlying distribution. When the train and test distributions do not match, a phenomenon known as domain shift, such models are likely to encounter performance drops.

Despite the growing availability of heterogeneous data, many NLP domains still lack the amounts of labeled data required to feed data-hungry neural models, and in some domains and languages even unlabeled data is scarce. As a result, the problem of domain adaptation, training an algorithm on annotated data from one or more source domains, and applying it to other target domains, is a fundamental challenge that has to be solved in order to make NLP technology available for most world languages and textual domains.

Domain Adaptation (DA) is hence the focus of this workshop. Particularly, the topics of the workshop include, but are not restricted to:

• Novel DA algorithms addressing existing and new assumptions (e.g. assuming or not assuming unlabeled data from the source and target domains, making certain assumptions on the differences between the source and target domain distributions, etc.).
• Introducing and exploring novel or under-explored DA setups, aiming towards realistic and applicable ones (e.g., one-to-many DA, many-to-many DA, DA when the target domain is unknown when training on the source domain, and source-free DA where just a source model is available but there is no access to source data).
• Extending DA research to new domains and tasks through both novel datasets and algorithmic approaches.
• Proposing novel zero-shot and few-shot algorithms and discussing their relevance for DA..
• Exploring the similarities and differences between algorithmic approaches to DA, cross-lingual, and cross-task learning.
• A conceptual discussion of the definitions of fundamental concepts such as domain, transfer as well as zero-shot and few-shot learning.
• Novel approaches to evaluation of DA methods under different assumptions on data availability (e.g. evaluation without access to target domain labeled data and even with small amounts of target domain unlabeled data).
• Thorough empirical comparisons of existing DA methods on existing and novel tasks, datasets, and setups.

Important Dates:

• Jan 18, 2021 – Submission deadline.


• Jan 24, 2021 – Submission deadline (Extension).


• Feb 18, 2021 – Notification of acceptance.


• Mar 1, 2021 – Camera-ready papers due.


• April 20, 2021 – Workshop Dates.

Submissions

The workshop will have two tracks: archival and non-archival. Only archival papers will be included in the proceedings as archival publications. All submissions should be in PDF format, follow the official EACL 2021 style guidelines, and be submitted via softconf, through the submission link provided below.

In the archival track, we invite the submission of long and short papers, describing original and unpublished research on topics related to the main workshop themes. Long papers may consist of up to 8 pages of content + references. Short papers may consist of up to 4 pages of content + references. Readable supplementary material can be added after references, in the appendices section. Submissions in this track should be anonymous. Upon acceptance, both types of papers will be given one (1) additional page of content. Authors are encouraged to use this additional page for addressing reviewers’ comments in the final version.

In the non-archival track, we invite extended abstracts that may consist of up to 4 pages of content + references. Extended abstracts describe preliminary work or results that have already been published, or work in progress that will be later submitted to archival venues. In this track we also allow the submission of papers that were published in top-tier venues over the last few years, in cases the authors believe that presenting these papers will contribute to the discussion at the workshop. Such papers can be submitted as a PDF file according to the format of the conference or journal in which they were originally published and papers should indicate this at submission time.

In both tracks, we welcome both empirical and theoretical papers, as well as opinion and discussion papers.

Best Paper Prizes

Thanks to generous support from our sponsors, we will be awarding prizes to the best paper submissions. More details regarding the amount of winning prizes and eligibility for the prizes will be announced soon.

Presentations

Accepted papers will also be presented as posters or participate in a Q&A session. Both tracks will be asked to pre-record a talk describing their work and contributions, but papers in the non-archival track that have already been presented in another meeting will also get the opportunity to provide a link to their original talk.

Submission link

Contact Email