Search Results for author: Thierry Etchegoyhen

Found 14 papers, 0 papers with code

To Case or not to case: Evaluating Casing Methods for Neural Machine Translation

no code implementations LREC 2020 Thierry Etchegoyhen, Harritxu Gete

We present a comparative evaluation of casing methods for Neural Machine Translation, to help establish an optimal pre- and post-processing methodology.

Machine Translation Translation

STACC, OOV Density and N-gram Saturation: Vicomtech's Participation in the WMT 2018 Shared Task on Parallel Corpus Filtering

no code implementations WS 2018 Andoni Azpeitia, Thierry Etchegoyhen, Eva Mart{\'\i}nez Garcia

To address the specifics of the corpus filtering task, which features significant volumes of noisy data, the core method was expanded with a penalty based on the amount of unknown words in sentence pairs.

Machine Translation Outlier Detection

Weighted Set-Theoretic Alignment of Comparable Sentences

no code implementations WS 2017 Andoni Azpeitia, Thierry Etchegoyhen, Eva Mart{\'\i}nez Garcia

This article presents the STACCw system for the BUCC 2017 shared task on parallel sentence extraction from comparable corpora.

Machine Translation

Exploiting a Large Strongly Comparable Corpus

no code implementations LREC 2016 Thierry Etchegoyhen, Andoni Azpeitia, Naiara P{\'e}rez

The EITB corpus, a strongly comparable corpus in the news domain, is to be shared with the research community, as an aid for the development and testing of methods in comparable corpora exploitation, and as basis for the improvement of data-driven machine translation systems for this language pair.

Machine Translation Translation

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