Document-level Machine Translation For Scientific Texts - Institut des Systèmes Intelligents et de Robotique Access content directly
Reports Year : 2023

Document-level Machine Translation For Scientific Texts

Abstract

While neural machine translation has seen significant progress during recent years at sentencelevel, translating full documents remains a challenge to efficiently incorporate document-level context. Various approaches have been proposed, but most of them consider only one to three previous source and/or target sentences as the context. This is not sufficient to faithfully translate some language phenomena, like lexical consistency and document coherence, especially in some scientific texts. In this work, we conducted experiments to include full contextual context and investigate the impact of all the past / future sentences on the source side with a context ablation study, on some abstracts from scientific publications. Our results show that future context is more influential than the past source context, and in our experiments, the Transformer architecture performs much better to translate the beginning of a long document than the end.
Fichier principal
Vignette du fichier
main.pdf (636.43 Ko) Télécharger le fichier
supplementary_material.pdf (128.11 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04258660 , version 1 (25-10-2023)
hal-04258660 , version 2 (04-11-2023)

Identifiers

  • HAL Id : hal-04258660 , version 1

Cite

Ziqian Peng. Document-level Machine Translation For Scientific Texts. ISIR, Université Pierre et Marie Curie UMR CNRS 7222. 2023. ⟨hal-04258660v1⟩
37 View
42 Download

Share

Gmail Facebook X LinkedIn More