Document Sub-structure in Neural Machine Translation

Radina Dobreva, Jie Zhou, Rachel Bawden

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationProceedings of the 12th Language Resources and Evaluation Conference (LREC 2020)
PublisherEuropean Language Resources Association (ELRA)
Number of pages11
ISBN (Electronic)979-10-95546-34-4
Publication statusPublished - 16 May 2020
Event12th Language Resources and Evaluation Conference - Le Palais du Pharo, Marseille, France
Duration: 11 May 202016 May 2020
Conference number: 12


Conference12th Language Resources and Evaluation Conference
Abbreviated titleLREC 2020
Internet address


  • Neural machine translation
  • document structure
  • corpus creation
  • context
  • Wikipedia
  • Parallel corpus


Dive into the research topics of 'Document Sub-structure in Neural Machine Translation'. Together they form a unique fingerprint.

Cite this