Detecting context-dependent sentences in parallel corpora

Rachel Bawden, Thomas Lavergne, Sophie Rosset


Abstract
In this article, we provide several approaches to the automatic identification of parallel sentences that require sentence-external linguistic context to be correctly translated. Our long-term goal is to automatically construct a test set of context-dependent sentences in order to evaluate machine translation models designed to improve the translation of contextual, discursive phenomena. We provide a discussion and critique that show that current approaches do not allow us to achieve our goal, and suggest that for now evaluating individual phenomena is likely the best solution.
Anthology ID:
2018.jeptalnrecital-court.22
Volume:
Actes de la Conférence TALN. Volume 1 - Articles longs, articles courts de TALN
Month:
5
Year:
2018
Address:
Rennes, France
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
ATALA
Note:
Pages:
393–400
Language:
URL:
https://aclanthology.org/2018.jeptalnrecital-court.22
DOI:
Bibkey:
Cite (ACL):
Rachel Bawden, Thomas Lavergne, and Sophie Rosset. 2018. Detecting context-dependent sentences in parallel corpora. In Actes de la Conférence TALN. Volume 1 - Articles longs, articles courts de TALN, pages 393–400, Rennes, France. ATALA.
Cite (Informal):
Detecting context-dependent sentences in parallel corpora (Bawden et al., JEP/TALN/RECITAL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2018.jeptalnrecital-court.22.pdf