Document Sub-structure in Neural Machine Translation

Radina Dobreva, Jie Zhou, Rachel Bawden


Abstract
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.
Anthology ID:
2020.lrec-1.451
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
3657–3667
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.451
DOI:
Bibkey:
Cite (ACL):
Radina Dobreva, Jie Zhou, and Rachel Bawden. 2020. Document Sub-structure in Neural Machine Translation. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3657–3667, Marseille, France. European Language Resources Association.
Cite (Informal):
Document Sub-structure in Neural Machine Translation (Dobreva et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.451.pdf
Code
 radidd/Doc-substructure-NMT