Výsledky vyhledávání - "Etchegoyhen, Thierry"

Report

Does Context Help Mitigate Gender Bias in Neural Machine Translation?

Autor: Gete, Harritxu, Etchegoyhen, Thierry

Neural Machine Translation models tend to perpetuate gender bias present in their training data distribution. Context-aware models have been previously suggested as a means to mitigate this type of bias. In this work, we examine this claim by analysi

Externí odkaz: http://arxiv.org/abs/2406.12364

Zobrazit plný text záznamu

Report

Automating Easy Read Text Segmentation

Autor: Calleja, Jesús, Etchegoyhen, Thierry, Ponce, David

Easy Read text is one of the main forms of access to information for people with reading difficulties. One of the key characteristics of this type of text is the requirement to split sentences into smaller grammatical segments, to facilitate reading.

Externí odkaz: http://arxiv.org/abs/2406.11464

Zobrazit plný text záznamu

Report

Promoting Target Data in Context-aware Neural Machine Translation

Autor: Gete, Harritxu, Etchegoyhen, Thierry

Standard context-aware neural machine translation (NMT) typically relies on parallel document-level data, exploiting both source and target contexts. Concatenation-based approaches in particular, still a strong baseline for document-level NMT, prepen

Externí odkaz: http://arxiv.org/abs/2402.06342

Zobrazit plný text záznamu

Report

Split and Rephrase with Large Language Models

Autor: Ponce, David, Etchegoyhen, Thierry, Pérez, Jesús Calleja, Gete, Harritxu

The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facilitate the processing of complex texts for humans and machines alike. I

Externí odkaz: http://arxiv.org/abs/2312.11075

Zobrazit plný text záznamu

Akademický článek

Efficient document alignment across scenarios

Autor: Azpeitia, Andoni, Etchegoyhen, Thierry

Publikováno v: Machine Translation, 2019 Sep 01. 33(3), 205-237.

Externí odkaz: https://www.jstor.org/stable/45221883

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Automatic removal of identifying information in oﬀicial EU languages for public administrations : the MAPA Project

The European MAPA (Multilingual Anonymisation for Public Administrations) project aims at developing an open-source solution for automatic de-identification of medical and legal documents. We introduce here the context, partners and aims of the proje

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3549::400257287638bf42cc43476223487872
https://www.um.edu.mt/library/oar/handle/123456789/70771

Zobrazit plný text záznamu

Neural Machine Translation of Basque

Autor: Etchegoyhen, Thierry, Martínez Garcia, Eva, Azpeitia, Andoni, Labaka Intxauspe, Gorka, Alegría Loinaz, Iñaki, Cortés Etxabe, Itziar, Jauregi Carrera, Amaia, Ellakuria, Igor, Martin, Maite, Calonge, Eusebi

Publikováno v: RUA. Repositorio Institucional de la Universidad de Alicante
Universidad de Alicante (UA)

We describe the first experimental results in neural machine translation for Basque. As a synthetic language featuring agglutinative morphology, an extended case system, complex verbal morphology and relatively free word order, Basque presents a larg

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::a67eeabde2c8a46d43ca5d10b4644c95
http://hdl.handle.net/10045/76024

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání