Hierarchical Document Encoder for Parallel Corpus Mining

Mandy Guo, Yinfei Yang, Keith Stevens, Daniel Cer, Heming Ge, Yun-hsuan Sung, Brian Strope, Ray Kurzweil


Abstract
We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings; (ii) a neural bag-of-words (BoW) document encoding model; (iii) a hierarchical multilingual document encoder (HiDE) that builds on our sentence-level model. The results show document embeddings derived from sentence-level averaging are surprisingly effective for clean datasets, but suggest models trained hierarchically at the document-level are more effective on noisy data. Analysis experiments demonstrate our hierarchical models are very robust to variations in the underlying sentence embedding quality. Using document embeddings trained with HiDE achieves the state-of-the-art on United Nations (UN) parallel document mining, 94.9% P@1 for en-fr and 97.3% P@1 for en-es.
Anthology ID:
W19-5207
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)
Month:
August
Year:
2019
Address:
Florence, Italy
Venues:
ACL | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–72
Language:
URL:
https://www.aclweb.org/anthology/W19-5207
DOI:
10.18653/v1/W19-5207
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-5207.pdf