Field linguistics plays a crucial role in the development of linguistic theory and universal language modeling, as it provides uncontested, the only way to obtain structural data about the rapidly diminishing diversity of natural languages.
The Field matters workshop aims to bring together the urgent needs of field linguists and the vast community of NLP practitioners, developing up-to-date NLP tools for easier, faster, more reliable data collection and annotation.
We are particularly interested in the following topics:
- Application of NLP to field linguistics workflow;
- The impact, benefits, and harms of NLP-assisted fieldwork;
- Transfer learning for under-resourced language processing;
- The use of fieldwork data to build NLP systems;
- Modeling morphology and syntax of typologically diverse languages in the low-resource setting;
- Speech processing for under-resourced languages;
- Machine-readable field linguistic datasets and computational analysis of field linguistics datasets;
- Using technology to preserve culture via language;
- Improving ways of interaction with Indigenous communities.
We accept three types of papers:
- short archival submissions: 4-page papers that present new work;
- long archival submissions: 8-page papers that present new work;
- non-archival submissions: abstracts (2-page) or papers (up to 8-page) that can present already published work or work in progress (note that we accept non-archival submissions even after the main deadline).
We offer the following ways of presenting the papers:
- the main oral presentation;
- poster presentation.
The way a paper will be presented will be determined during the review process.
All submissions should be anonymized. We are subjected to the ACL Anonymity Policy. Following ACL's policy for review and citation, no anonymity period will be required.
Papers posted to preprint servers such as arXiv can be submitted without any restrictions on when they were posted.
The workshop will run its own review process, and papers can be submitted directly to the workshop via OpenReview (link TBA; cf. workshop website: https://field-matters.github.io).
The workshop will take place at EACL 2027.
Both papers and abstracts must follow the ACL format. Please do not modify these style files.
For Pre-reviewed (ARR) submissions and Findings articles
-----
Pre-reviewed (ARR) submissions:
Please submit the article through the OpenReview platform.
The title of the submission should start with [ARR], and the submission file should contain both the article and the link to the ARR reviews.
Findings articles:
Our workshop also offers the opportunity for researchers with accepted Findings articles to present their work.
Please send us the article per email (fieldmattersworkshop [at] gmail.com) with the PDF. Acceptance for presentation will be based on the relevance to the workshop topics.
Shared Task
-----
For our 2027 edition, Field Matters will organize a Shared Task on Automatic Interlinear Glossing.
The task is to predict interlinear glosses, which are morpheme-level linguistic annotations (e.g., Flaschen (bottles) in German can be labelled as bottle-PL), notably used in field linguistics. Ultimately, glossing systems aim to help field linguists with the annotation task for languages under documentation, as it is mainly performed manually with little automation.
More details regarding the task, datasets, evaluation, and models are going to be announced on the dedicated page: https://field-matters.github.io/sharedtask2027.
The Shared Task will be aligned with the general workshop dates regarding system descriptions.
Important dates
-----
- Direct Submission deadline: December 15, 2026
- Pre-reviewed (ARR) submission deadline: December 22, 2026
- Notification of acceptance: January 11, 2027
- Camera-ready deadline: January 22, 2027
- Workshop dates: March 9-14, 2027
All deadlines are 23:59 UTC-12 ('Anywhere on Earth').
Organizers
-----
- Éric Le Ferrand (University at Buffalo)
- Elena Klyachko (independent researcher)
- Shu Okabe (TUM)
- Oleg Serikov (Palisade Research)
- Ekaterina Voloshina (University of Gothenburg, Chalmers University of Technology)
- Karina Sheifer (UC Santa Barbara)