Papers by Maite Melero
Unmasking Biases: Exploring Gender Bias in English-Catalan Machine Translation through Tokenization Analysis and Novel Dataset (2024.lrec-main)
Copied to clipboard
| Challenge: | a new dataset focuses on gender-neutral terms that necessitate gendered translations in Catalan. |
| Approach: | They propose to use a new dataset to evaluate gender bias in machine translation . they train four MT systems using different tokenization techniques . |
| Outcome: | The proposed dataset focuses on gender-neutral terms necessitating gendered translations in Catalan. |
On the Multilingual Capabilities of Very Large-Scale English Language Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Generative Pre-trained Transformers (GPTs) have been scaled to unprecedented sizes in the history of machine learning. |
| Approach: | They investigate the potential and limits of Generative Pre-trained Transformers in three tasks . they find it can be almost as useful for many languages as it is for English . |
| Outcome: | The proposed model can perform tasks in five different languages, and its potential is explored . it can learn from a few examples "via text interaction" and is scalable to many languages . |
Unsupervised Machine Translation in Real-World Scenarios (2022.lrec-1)
Copied to clipboard
Ona de Gibert Bonet, Iakes Goenaga, Jordi Armengol-Estapé, Olatz Perez-de-Viñaspre, Carla Parra Escartín, Marina Sanchez, Mārcis Pinnis, Gorka Labaka, Maite Melero
| Challenge: | a recent study has shown that unsupervised methods rely on monolingual corpora to build MT systems. |
| Approach: | They present the results of the MT4All CEF project using monolingual corpora . they propose to generate bilingual dictionaries and translation models from monolingual data . |
| Outcome: | The proposed method generates bilingual dictionaries and translation models from monolingual corpora . results show that it is comparable to general domain supervised translation . |
Spanish Datasets for Sensitive Entity Detection in the Legal Domain (2022.lrec-1)
Copied to clipboard
| Challenge: | The de-identification of sensible data is essential for data sharing and reuse, both for research and commercial purposes. |
| Approach: | They propose to use four datasets annotated for named entity detection in Spanish to fine-tune models for the task of named entity-detection. |
| Outcome: | The proposed model is based on four datasets annotated for named entity detection in Spanish with an estimated error rate of 14%. |
Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan (2021.findings-acl)
Copied to clipboard
Jordi Armengol-Estapé, Casimiro Pio Carrino, Carlos Rodriguez-Penagos, Ona de Gibert Bonet, Carme Armentano-Oller, Aitor Gonzalez-Agirre, Maite Melero, Marta Villegas
| Challenge: | Multilingual language models have been a crucial breakthrough for under-resourced languages . however, the superiority of language-specific models has already been proven for underresourced ones . |
| Approach: | They propose to build a monolingual monolingual model that is comparable to state-of-the-art large multilingual models. |
| Outcome: | The proposed model consistently outperforms state-of-the-art models across tasks and settings. |