Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides

Ruchit Agrawal, Marco Turchi, Matteo Negri


Abstract
A salient feature of Neural Machine Translation (NMT) is the end-to-end nature of training employed, eschewing the need of separate components to model different linguistic phenomena. Rather, an NMT model learns to translate individual sentences from the labeled data itself. However, traditional NMT methods trained on large parallel corpora with a one-to-one sentence mapping make an implicit assumption of sentence independence. This makes it challenging for current NMT systems to model inter-sentential discourse phenomena. While recent research in this direction mainly leverages a single previous source sentence to model discourse, this paper proposes the incorporation of a context window spanning previous as well as next sentences as source-side context and previously generated output as target-side context, using an effective non-recurrent architecture based on self-attention. Experiments show improvement over non-contextual models as well as contextual methods using only previous context.
Anthology ID:
2018.eamt-main.1
Volume:
Proceedings of the 21st Annual Conference of the European Association for Machine Translation
Month:
May
Year:
2018
Address:
Alicante, Spain
Editors:
Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović, Celia Rico, André Martins, Joachim Van den Bogaert, Mikel L. Forcada
Venue:
EAMT
SIG:
Publisher:
Note:
Pages:
31–40
Language:
URL:
https://aclanthology.org/2018.eamt-main.1
DOI:
Bibkey:
Cite (ACL):
Ruchit Agrawal, Marco Turchi, and Matteo Negri. 2018. Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, pages 31–40, Alicante, Spain.
Cite (Informal):
Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides (Agrawal et al., EAMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.eamt-main.1.pdf