Papers by Iakes Goenaga
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 . |
Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of LLM-Generated Medical Explanatory Arguments (2025.coling-main)
Copied to clipboard
Iker De la Iglesia, Iakes Goenaga, Johanna Ramirez-Romero, Jose Maria Villa-Gonzalez, Josu Goikoetxea, Ander Barrena
| Challenge: | Evaluating LLM-generated text has become a key challenge in domain-specific contexts like the medical field. |
| Approach: | They propose a method to evaluate LLM-generated medical explanatory arguments using Proxy Tasks and rankings to align results with human evaluation criteria. |
| Outcome: | The proposed evaluation method is robust against adversarial attacks, including the assessment of non-argumentative text. |
IxaMed at PharmacoNER Challenge 2019 (D19-57)
Copied to clipboard
| Challenge: | The aim of this paper is to present our approach in the PharmacoNER 2019 task. |
| Approach: | They propose to use a Bi-LSTM with a CRF to identify named entities from clinical case studies written in Spanish. |
| Outcome: | The proposed approach achieves the best score (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records with contextual string embedds. |