Document Sub-structure in Neural Machine Translation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Document Sub-structure in Neural Machine Translation

Radina Dobreva
  • Fonction : Auteur
  • PersonId : 1074784
Rachel Bawden

Résumé

Current approaches to machine translation (MT) either translate sentences in isolation, disregarding the context they appear in, or model context at the level of the full document, without a notion of any internal structure the document may have. In this work we consider the fact that documents are rarely homogeneous blocks of text, but rather consist of parts covering different topics. Some documents, such as biographies and encyclopedia entries, have highly predictable, regular structures in which sections are characterised by different topics. We draw inspiration from Louis and Webber (2014) who use this information to improve statistical MT and transfer their proposal into the framework of neural MT. We compare two different methods of including information about the topic of the section within which each sentence is found: one using side constraints and the other using a cache-based model. We create and release the data on which we run our experiments - parallel corpora for three language pairs (Chinese-English, French-English, Bulgarian-English) from Wikipedia biographies, which we extract automatically, preserving the boundaries of sections within the articles.
Fichier principal
Vignette du fichier
LREC_submission.pdf (1.1 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02900568 , version 1 (16-07-2020)

Identifiants

  • HAL Id : hal-02900568 , version 1

Citer

Radina Dobreva, Jie Zhou, Rachel Bawden. Document Sub-structure in Neural Machine Translation. 12th Language Resources and Evaluation Conference, 2020, Marseille, France. pp.3657-3667. ⟨hal-02900568⟩
19 Consultations
24 Téléchargements

Partager

Gmail Facebook X LinkedIn More