📢 CALL FOR PAPERS

We organise a Networking Symposium on Latin American NLP (LANLP), focusing on natural language processing for the diverse languages of the Iberian Peninsula and Latin America. This region includes major world languages (e.g. Spanish (~558M speakers), Portuguese (~267M) as well as regional and indigenous languages. For example, Latin America alone hosts tens of millions of speakers of Quechua (~10M), Guaraní (>6M), Nahuatl (~2M), Aymara (~2M), among many others. Such languages are highly under‐resourced: over 88% of the world’s languages remain largely unsupported by language technologies. This networking event addresses that gap by promoting collaboration on ethically and culturally sensitive resource creation, evaluation, and novel methods for low-resource multilingual NLP in Iberian and Latin American languages and varieties. Our goal is to bring together communities (SEPLN, CLARIAH-ES, PROPOR and AmericasNLP) to share cutting-edge research, language resources, and best practices.

LANLP focuses on community-driven resource development and evaluation for Iberian languages, and diverse Latin American languages (including indigenous and minority languages). We aim to bridge regional communities: for instance, past forums like OpenCor note that “Latin American and Iberian communities... did not have an established event” to share initiatives, corpora and tools. LANLP fills this gap, fostering new contacts between Iberian and Latin American NLP research groups. The goals are to (1) highlight challenges in processing these languages, (2) share novel datasets and models, and (3) catalyze future collaborations and shared tasks. We emphasize both academic rigor and community inclusivity, encouraging contributions from established researchers and grassroots language advocates alike.

Topics of Interest

We invite submissions on topics including (but not limited to):

• Language resource creation: Corpora, lexicons, and annotations for Iberian and Latin American languages (text, speech, multimodal).

• LLMs opportunities and challenges: Small Language Models, synthetic data, mitigating biases, linguistic inequalities, data scarcity, language domination.

• Multilingual transfer & modeling: Cross-lingual and multilingual representations, transfer learning, and embedding methods that bridge Spanish, Portuguese, varieties and minority languages.

• Machine translation & generation: MT, summarization, and language generation for Spanish, Portuguese, and low-resource languages (e.g., Quechua, Aymara, Nahuatl).

• Speech and audio processing: ASR, TTS, and spoken language resources for under-resourced languages and regional dialects (e.g. indigenous languages, Brazilian Portuguese, Latin American Spanish).

• Dialectal and code-switching NLP: Identification and handling of dialectal variation and code-switching (e.g. Spanish–Portuguese code-mixing, Spanish–indigenous language contact).

• Morphology and syntax: Analysis and tagging for morphologically rich or under-documented languages (e.g. Basque, Mapudungun, Bribri) using universal dependencies or other frameworks.

• Domain-specific NLP: Social media, sentiment, hate-speech detection, and other tasks in Iberian and Latin American language contexts (e.g. Latin American social media analysis).

• Digital humanities & cultural heritage: NLP for historical texts, literature, and cultural content in Spanish, Portuguese, and regional languages.

• Community-driven methods: Crowdsourcing, citizen science, and participatory approaches for data collection and annotation in these languages.

• Evaluation and benchmarks: Development of evaluation metrics and benchmarks tailored to low-resource Iberian/Latin languages.

• Ethical and social issues: Fairness, bias, and indigenous language rights in NLP; collaboration with native speaker communities; data governance and sustainability of resources..

Important Dates

📧Submission Instructions

We invite non anonymous submissions in English, Spanish or Portuguese on the topics of interest between 4 and 8 pages of content. The page limit of 8 pages does not include acknowledgements, references, potential Ethics Statements and discussion on Limitations in line with the policy of the main LREC conference. All submissions must follow the LREC stylesheet (https://lrec2026.info/authors-kit/).

Any submissions which are over-length, poorly formatted or make excessive use of appendices to circumvent page limits are liable to desk-rejection.

At the time of submission, authors are offered the opportunity to share related language resources with the community. All repository entries are linked to the LRE Map (https://lremap.elra.info/), which provides metadata for the resource.

🌐 Accepted Languages

Papers can be submitted in English, Spanish, or Portuguese.

📤 How to Submit

Submission platform: [TBA - To Be Announced]

The submission link will be available in January 2026.  

Please prepare your paper following the LREC stylesheet 

in advance. 

📧Organizing Commitee

• Luis Chiruzzo Inco (AmericasNLP, luischir@fing.edu.uy)

• Pablo Gamallo (PROPOR, CiTIUS, pablo.gamallo@usc.gal)  

• Rafael Muñoz Guillena (SEPLN, CENID, UA, rafael@dlsi.ua.es)

• German Rigau Claramunt (CLARIAH-ES. HiTZ Center, EHU, german.rigau@ehu.eus)