A Comparison between NMT and PBSMT Performance for Translating Noisy User-Generated Content - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

A Comparison between NMT and PBSMT Performance for Translating Noisy User-Generated Content

Abstract

This work compares the performances achieved by Phrase-Based Statistical Ma- chine Translation systems (PBSMT) and attention-based Neural Machine Transla- tion systems (NMT) when translating User Generated Content (UGC), as encountered in social medias, from French to English. We show that, contrary to what could be ex- pected, PBSMT outperforms NMT when translating non-canonical inputs. Our error analysis uncovers the specificities of UGC that are problematic for sequential NMT architectures and suggests new avenue for improving NMT models.
Fichier principal
Vignette du fichier
nodalida2019.pdf (1.39 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02270524 , version 1 (25-08-2019)

Identifiers

  • HAL Id : hal-02270524 , version 1

Cite

José Carlos Rosales Nunez, Djamé Seddah, Guillaume Wisniewski. A Comparison between NMT and PBSMT Performance for Translating Noisy User-Generated Content. The 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19), Sep 2019, Turku, Finland. ⟨hal-02270524⟩
279 View
183 Download

Share

Gmail Facebook X LinkedIn More