Exploiting Sentence Order in Document Alignment

Brian Thompson, Philipp Koehn


Abstract
We present a simple document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring. Our method results in 61% relative reduction in error compared to the best previously published result on the WMT16 document alignment shared task. Our method improves downstream MT performance on web-scraped Sinhala–English documents from ParaCrawl, outperforming the document alignment method used in the most recent ParaCrawl release. It also outperforms a comparable corpora method which uses the same multilingual embeddings, demonstrating that exploiting sentence order is beneficial even if the end goal is sentence-level bitext.
Anthology ID:
2020.emnlp-main.483
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5997–6007
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.483
DOI:
10.18653/v1/2020.emnlp-main.483
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.483.pdf