Search Results for author: Inigo Jauregi Unanue

Found 13 papers, 4 papers with code

Pretrained Language Models and Backtranslation for English-Basque Biomedical Neural Machine Translation

no code implementations WMT (EMNLP) 2020 Inigo Jauregi Unanue, Massimo Piccardi

This paper describes the machine translation systems proposed by the University of Technology Sydney Natural Language Processing (UTS_NLP) team for the WMT20 English-Basque biomedical translation tasks.

Machine Translation Natural Language Processing +2

A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization

1 code implementation ACL 2022 Jacob Parnell, Inigo Jauregi Unanue, Massimo Piccardi

Multi-document summarization (MDS) has made significant progress in recent years, in part facilitated by the availability of new, dedicated datasets and capacious language models.

Document Summarization Multi-Document Summarization

RewardsOfSum: Exploring Reinforcement Learning Rewards for Summarisation

no code implementations ACL (spnlp) 2021 Jacob Parnell, Inigo Jauregi Unanue, Massimo Piccardi

To date, most abstractive summarisation models have relied on variants of the negative log-likelihood (NLL) as their training objective.

reinforcement-learning

Learning Neural Textual Representations for Citation Recommendation

no code implementations8 Jul 2020 Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi

With the rapid growth of the scientific literature, manually selecting appropriate citations for a paper is becoming increasingly challenging and time-consuming.

Citation Recommendation

Regressing Word and Sentence Embeddings for Regularization of Neural Machine Translation

no code implementations30 Sep 2019 Inigo Jauregi Unanue, Ehsan Zare Borzeshi, Massimo Piccardi

This is a serious issue for low-resource language pairs and many specialized translation domains that are inherently limited in the amount of available supervised data.

Machine Translation Sentence Embeddings +1

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

1 code implementation29 Jun 2017 Inigo Jauregi Unanue, Ehsan Zare Borzeshi, Massimo Piccardi

Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary.

BIG-bench Machine Learning Clinical Concept Extraction +4

Cannot find the paper you are looking for? You can Submit a new open access paper.