Hierarchical Document Encoder for Parallel Corpus Mining.

FOURTH CONFERENCE ON MACHINE TRANSLATION (WMT 2019), VOL 1: RESEARCH PAPERS, (2019): 64-72

Cited by: 0|Views50
EI

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 bagof-words (BoW) document encoding model; (iii) a hierarchical multilingual document e...More

Code:

Data:

ZH
Full Text
Bibtex
Your rating :
0

 

Tags
Comments