Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427149" target="_blank" >RIV/00216208:11320/19:10427149 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/W19-5418" target="_blank" >https://www.aclweb.org/anthology/W19-5418</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task

Popis výsledku v původním jazyce

In this work, we give a description of the TALP-UPC systems submitted for the WMT19 Biomedical Translation Task. Our proposed strategy is NMT model-independent and relies only on one ingredient, a biomedical terminology list. We first extracted such a terminology list by labelling biomedical words in our training dataset using the BabelNet API. Then, we designed a data preparation strategy to insert the terms information at a token level. Finally, we trained the Transformer model with this terms-informed data. Our best-submitted system ranked 2nd and 3rd for Spanish-English and English-Spanish translation directions, respectively.

Název v anglickém jazyce

Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task

Popis výsledku anglicky

In this work, we give a description of the TALP-UPC systems submitted for the WMT19 Biomedical Translation Task. Our proposed strategy is NMT model-independent and relies only on one ingredient, a biomedical terminology list. We first extracted such a terminology list by labelling biomedical words in our training dataset using the BabelNet API. Then, we designed a data preparation strategy to insert the terms information at a token level. Finally, we trained the Transformer model with this terms-informed data. Our best-submitted system ranked 2nd and 3rd for Spanish-English and English-Spanish translation directions, respectively.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů