Papers by German Rigau

16 papers
Building Named Entity Recognition Taggers via Parallel Corpora (L18-1)

Copied to clipboard

Challenge: Existing methods to generate semantic processors for languages lacking hand curated data are inefficiently slow and unaffordable in terms of human resources and economic costs.
Approach: They propose to use statistical word alignments to project annotations from multiple sources to a target language.
Outcome: The proposed method is effective to transport NER annotations across languages . it can generate a good statistical model for a new target language .
Cross-checking WordNet and SUMO Using Meronymy (L18-1)

Copied to clipboard

Challenge: Existing methods to validate knowledge encoded in WordNet, SUMO and their mapping have been mainly manual .
Approach: They propose to use WordNet and SUMO to validate knowledge by using automated theorem provers to evaluate the competency of SU MO-based ontologies.
Outcome: The proposed method enables validation of some pieces of information and also the detection of missing information or inconsistencies among knowledge resources.
MedMT5: An Open-Source Multilingual Text-to-Text LLM for the Medical Domain (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on large language models for medical applications have focused on a single language . medical mT5 outperforms both encoders and similar sized text-to-text models in English, French, and Italian benchmarks .
Approach: They propose to train Medical mT5, the first open-source text-to-text multilingual model for the medical domain.
Outcome: The proposed model outperforms encoders and similar sized models on the Spanish, French, and Italian benchmarks while being competitive with current state-of-the-art models in English.
Machine Translation for Low-Resource Languages through Monolingual Data and LLM: A Case Study of English-to-Basque (2026.eacl-srw)

Copied to clipboard

Challenge: Existing LLMs do not translate well from English to Basque, but they yield an acceptable performance in the reverse direction.
Approach: They propose to use a Basque monolingual corpora to train an LLM-based MT system . they use 'sovereignty fine tuning' to generate parallel corporata, and then use preference optimization .
Outcome: The proposed system improves translation quality in English-to-Basque direction while requiring limited data for low-resource languages.
Developing New Linguistic Resources and Tools for the Galician Language (L18-1)

Copied to clipboard

Challenge: Existing resources and tools for the Galician language are lacking for other less-resourced languages, such as statistical tools for lemmatization and Named Entity Recognition.
Approach: They propose to develop a manually revised corpus for POS tagging and lemmatization, and a new manually annotated corpus to train existing statistical tools for the Galician language.
Outcome: The proposed resources include a new corpus for POS tagging and lemmatization, and a manually annotated corpus to handle Named Entity recognition.
Biomedical term normalization of EHRs with UMLS (L18-1)

Copied to clipboard

Challenge: Currently, there is no tool for this language and for this specific purpose.
Approach: They propose a multilingual and cross-lingual tool that searches for biomedical terms in clinical texts with the Unified Medical Language System (UMLS) Metathesaurus.
Outcome: The proposed tool performs biomedical term normalization in clinical texts with the unified medical language system (UMLS) Metathesaurus . it is based on Apache Lucene TM and is available on-line 2 .
Can LLMs Reason Like Doctors? Exploring the Limits of Large Language Models in Complex Medical Reasoning (2026.findings-eacl)

Copied to clipboard

Challenge: Large language models (LLMs) have shown remarkable progress in reasoning across multiple domains, but it remains unclear whether their abilities reflect genuine reasoning or sophisticated pattern matching.
Approach: They conduct one of the largest evaluations to date, assessing 77 LLMs . they select three medical question answering (QA) benchmarks targeting reasoning processes .
Outcome: The results highlight the need to improve specific reasoning strategies to better reflect medical decision-making.
This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have grammatical knowledge but fail to interpret negation . a recent study shows that LLMs struggle with negative sentences .
Approach: They propose to use a dataset to grasp LLMs' generalization and inference capability . they also fine-tuned models to assess whether the understanding of negation can be trained .
Outcome: The proposed model is able to generalize and infer negation in 400,000 sentences . but it is suboptimal when it comes to negation, a key step in natural language processing .
Multilingual Stance Detection in Tweets: The Catalonia Independence Corpus (2020.lrec-1)

Copied to clipboard

Challenge: stance detection is a method to determine the attitude of a text with respect to a specific topic or claim.
Approach: They propose a multilingual dataset for stance detection in Twitter for the Catalan and Spanish languages.
Outcome: The proposed dataset shows that it is well balanced for multilingual and cross-lingual research.
NUBes: A Corpus of Negation and Uncertainty in Spanish Clinical Texts (2020.lrec-1)

Copied to clipboard

Challenge: Currently, there are not many corpora that cover propositional aspects of meaning . these include factuality, uncertainty, opinions, beliefs, intentions or subjectivity .
Approach: They introduce the first version of the NUBes corpus (Negation and Uncertainty annotations in Biomedical texts in Spanish) . it includes an exhaustive comparison with similar corpora in Spanish and preliminary experiments using deep learning algorithms to validate the annotated dataset.
Outcome: The proposed corpus is compared with similar corpora in Spanish and performs preliminary experiments using deep learning algorithms.
T-Projection: High Quality Annotation Projection for Sequence Labeling Tasks (2023.findings-emnlp)

Copied to clipboard

Challenge: Annotation projection is a task of transporting labels from source to target language without high-quality training data.
Approach: They propose an annotation projection approach that leverages pretrained text2text models and machine translation technology to generate annotated data.
Outcome: The proposed approach outperforms existing methods on intrinsic and extrinsic tasks in 5 Indo-European and 8 low-resource African languages.
Benchmarking Meta-embeddings: What Works and What Does Not (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to build meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach.
Approach: They propose a unified framework for a fair and objective meta-embedding evaluation using intrinsic and extrinsic tasks.
Outcome: The proposed framework outperforms existing methods on intrinsic and extrinsic evaluation benchmarks and outperformed existing methods.
ClinIDMap: Towards a Clinical IDs Mapping for Data Interoperability (2022.lrec-1)

Copied to clipboard

Challenge: a tool for mapping identifiers between clinical ontologies and lexical resources is available.
Approach: They propose a tool for mapping identifiers between clinical ontologies and lexical resources.
Outcome: The proposed mapping tool can be used to enrich existing annotated corpora in multiple languages.
Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have proposed data-based cross-lingual transfer as an effective technique for cross-linguistic sequence labelling, but they have failed to perform well.
Approach: They propose to use data-based cross-lingual transfer to train supervised models from a source language to unlabelled target languages.
Outcome: The proposed techniques outperform data-based cross-lingual transfer approaches in a zero-shot setting.
IberoBench: A Benchmark for LLM Evaluation in Iberian Languages (2025.coling-main)

Copied to clipboard

Challenge: Existing multi-task benchmarks for Large Language Models are limited to English . a new benchmark is needed to evaluate models on a range of tasks .
Approach: They propose a multilingual, multi-task benchmark for Iberian languages built on the LM Evaluation Harness framework.
Outcome: The proposed benchmark covers 62 tasks divided into 179 subtasks and is available in Iberian, Basque, Catalan, Galician, European Spanish and European Portuguese.
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque (2025.emnlp-main)

Copied to clipboard

Challenge: Instructing language models with user intent requires large instruction datasets limited to a limited set of languages.
Approach: They propose to use existing LLMs and synthetically generated instructions to train models with user intent.
Outcome: The proposed model outperforms base non-instructed models on Basque without Basque instructions.

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