SOTAVerified

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

2019-08-01WS 2019Unverified0· sign in to hype

Casimiro Pio Carrino, Bardia Rafieian, Marta R. Costa-juss{\`a}, Jos{\'e} A. R. Fonollosa

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

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.

Tasks

Reproductions