Languages are the heart and soul of cultural identity and communication, and nowhere is this more evident than in the vibrant tapestry of Latin America and the Caribbean. With a rich linguistic diversity that spans Spanish, Portuguese, and numerous indigenous languages, the region offers a unique challenge and opportunity for Natural Language Processing (NLP) researchers. For NAACL 2024, we invite submissions to the special theme track on “Languages of Latin America”. This track is dedicated to taking stock of past research and developments in the field of NLP for Languages of Latin America and the Caribbean while charting the course for future investigations.
We seek both long and short papers that propose innovative directions for future research in this domain. We invite papers presenting research studies, conducting a comprehensive survey, or sharing insights through a position paper. We encourage submissions that contribute to our collective understanding of NLP’s role in the languages of Latin America and the Caribbean.
Submissions may employ a variety of relevant methods, including but not limited to machine learning, deep learning, natural language processing techniques, data mining, corpus linguistics, and cross-cultural analysis. We encourage interdisciplinary approaches that combine NLP with insights from linguistics, anthropology, and education to address the unique challenges and opportunities presented by the languages of Latin America and the Caribbean.
Possible Topics of Interest:
We welcome submissions on a wide range of topics related to NLP for Languages of Latin America and the Caribbean, including but not limited to:
- Challenges and opportunities in NLP for Latin American and Caribbean languages
- Computational methods for Latin American and Caribbean indigenous languages, including preservation, revitalization, usability, among many others
- Language technologies for education and learning in Latin America and the Caribbean
- Creation of linguistic resources and annotated data for Latin American and Caribbean languages
- Regionally-relevant NLP applications (sentiment analysis, translation, information extraction, etc.)
- Computational linguistics techniques for Latin American and Caribbean languages (morphological analysis, parsing, semantics, etc.)
- Historical overview of NLP research in the region
Difference between a theme paper and a regular paper
The distinctive feature of our special theme track lies in its dedicated focus on research questions and methodologies that revolve specifically around the languages of Latin America and the Caribbean. This track prioritizes contributions that explore the linguistic diversity, challenges, and unique opportunities presented by Latin American and Caribbean languages within the realm of Natural Language Processing (NLP). Submissions to this special theme are expected to emphasize how their research aligns with and advances the understanding and application of NLP in the context of Latin American and Caribbean languages.
In thinking about whether a paper belongs in the theme track or the regular track, consider how it provides insights into the future of NLP for Latin American and Caribbean languages. For example:
- A paper that explores sentiment analysis or emotion detection in social media content in Spanish may be relevant, but if evaluating only on standard corpus-based benchmarks, it would best fit the regular track. However, if the paper provides insights into regional attitudes and trends, it would be a good fit for the theme track.
- A resource paper that provides syntactic annotations to Portuguese should be a regular paper. More suitable for the special theme would be work that includes data on both Brazilian Portuguese and European Portuguese, with analyses of similarities and differences.
- A paper related to machine translation that focuses on the low resource problem and includes experiments on indigenous languages of Latin America should be a regular paper. It will fall within the scope of the special theme if it contributes language-specific technical innovations or addresses regional nuances such as dialectal variations, idiomatic expressions, and cultural references.
Some papers published in previous conferences and workshops that would have been appropriate for the theme are below. This list is far from exhaustive; there are many other possible directions.
- Challenges of language technologies for the indigenous languages of the Americas. Manuel Mager, Ximena Gutierrez-Vasques, Gerardo Sierra, Ivan Meza-Ruiz. COLING 2018.
- Neural Machine Translation Models with Back-Translation for the Extremely Low-Resource Indigenous Language Bribri. Isaac Feldman, Rolando Coto-Solano. COLING 2020.
- Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech. Adriana Guevara-Rukoz, Isin Demirsahin, Fei He, Shan-Hui Cathy Chu, Supheakmungkol Sarin, Knot Pipatsrisawat, Alexander Gutkin, Alena Butryna, Oddur Kjartansson. LREC 2020
- A survey of part-of-speech tagging approaches applied to K’iche’. Francis Tyers, Nick Howell. AmericasNLP 2021.
- Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yolóxochitl Mixtec. Jiatong Shi, et al. EACL 2021
- Use of NLP in the Context of Belief states of Ethnic Minorities in Latin America. Olga Kellert, Mahmud Zaman. AmericasNLP 2023.
- Regionalized models for Spanish language variations based on Twitter. Eric S. Tellez, Daniela Moctezuma, Sabino Miranda, Mario Graff, Guillermo Ruiz. Language Resources and Evaluation Journal. 2023
Submission for the special track will also run through ARR, using the same submission link as regular papers. Authors will be able to choose the track on the submission page. As with all other NAACL 2024 submissions, the special theme track also has until the December 15 Anywhere on Earth deadline. Reviewers for the special track will be instructed to give significant weight in their evaluations to how well the paper aligns with the theme.
Accepted papers will be presented either orally or as a poster. We anticipate having special sessions dedicated to the theme.
Events related to this theme at the conference
There will be other theme-related events at NAACL 2024. It has been confirmed that the Mexican Summer School on Natural Language Processing will be held in the days prior to the main conference. The AmericasNLP workshop is also confirmed. If you are interested in collaborating with ideas or suggestions for activities related to the topic, please contact us at firstname.lastname@example.org.