Papers by Ander Corral

7 papers
DIPLomA: Efficient Adaptation of Instructed LLMs to Low-Resource Languages via Post-Training Delta Merging (2025.findings-emnlp)

Copied to clipboard

Challenge: Using delta-based weight merging, open-weight instruction-tuned large language models can be efficiently adapted to low-resource languages without costly large-scale post-training.
Approach: They propose a delta-based instruction-preserving language adaptation strategy that decouples adaptation from post-training alignment by pretraining a foundational LLM on monolingual target-language data and then injecting instruction-following capabilities via delta-derived weight merging.
Outcome: The proposed method achieves significant gains in instruction-following, linguistic proficiency, and safety on Basque, Welsh, and Swahili while preserving the original model's multilingual performance.
TANDO: A Corpus for Document-level Machine Translation (2022.lrec-1)

Copied to clipboard

Challenge: Document-level Neural Machine Translation aims to increase the quality of neural translation models by taking into account contextual information.
Approach: They propose to use document-level corpus for Basque-Spanish language pairs to take into account contextual information and perform fine-grained evaluations of gender and gender.
Outcome: The proposed corpus is suitable for fine-grained evaluation of document-level machine translation systems.
How Well Can BERT Learn the Grammar of an Agglutinative and Flexible-Order Language? The Case of Basque. (2024.lrec-main)

Copied to clipboard

Challenge: Neural Language Models (NLMs) have demonstrated effectiveness in acquiring skills related to human language use.
Approach: They hypothesize that languages with complex grammar present substantial challenges during the pre-training phase . they constructed a test set that measures grammatical knowledge of BERT models trained under various pre-training configurations using corpus size, model size, number of epochs, and lemmatization.
Outcome: The proposed model is based on a student-based minimal pairs test set with a grammatically correct and an incorrect sentence.
Morphology Aware Source Term Masking for Terminology-Constrained NMT (2024.findings-eacl)

Copied to clipboard

Challenge: Recent research in terminology-constrained NMT systems focuses on data-driven approaches to generating translations.
Approach: They propose a method that appends target term lemmas to their corresponding source terms in the input sentence while retaining essential grammatical information.
Outcome: The proposed method improves on the “copy-and-inflect” method in two translation directions with different levels of source morphological complexity.
Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque (2025.naacl-long)

Copied to clipboard

Challenge: Large language models are typically optimized for resource-rich languages like English . however, the proprietary nature of these models makes them impractical for many researchers and developers.
Approach: They propose to develop large language models that can follow instructions in Basque . they focus on three key stages: pre-training, instruction tuning, and alignment with human preferences .
Outcome: The proposed models improve natural language understanding (NLU) of the foundational model by 12 points . the results show that the models can follow instructions in Basque with human preferences .
Not Enough Data to Pre-train Your Language Model? MT to the Rescue! (2023.findings-acl)

Copied to clipboard

Challenge: In recent years, transformer-based language models (LMs) have become the default approach for many NLP tasks.
Approach: They compare the performance of transformer-based language models with machine-translated corpora.
Outcome: The proposed model can be improved with real data, but further research is needed.
Automatic Speech Recognition for Gascon and Languedocian Variants of Occitan (2024.lrec-main)

Copied to clipboard

Challenge: a new system for automatic speech recognition is being developed for two main Occitan dialects . the difficulty lies in the fact that Occitian is a less-resourced language .
Approach: They propose to develop an automatic speech recognition system for two Occitan dialects . they use Kaldi, acoustic models, and Whisper to create a model from corpora .
Outcome: The proposed system is based on Kaldi and Whisper for two main Occitan dialects . the system is more robust than previous systems, and the results are promising .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations