Learning to translate from graded and negative relevance information

Laura Jehl, Stefan Riezler


Abstract
We present an approach for learning to translate by exploiting cross-lingual link structure in multilingual document collections. We propose a new learning objective based on structured ramp loss, which learns from graded relevance, explicitly including negative relevance information. Our results on English German translation of Wikipedia entries show small, but significant, improvements of our method over an unadapted baseline, even when only a weak relevance signal is used. We also compare our method to monolingual language model adaptation and automatic pseudo-parallel data extraction and find small improvements even over these strong baselines.
Anthology ID:
C16-1297
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
3156–3166
Language:
URL:
https://aclanthology.org/C16-1297
DOI:
Bibkey:
Cite (ACL):
Laura Jehl and Stefan Riezler. 2016. Learning to translate from graded and negative relevance information. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3156–3166, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Learning to translate from graded and negative relevance information (Jehl & Riezler, COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1297.pdf
Data
WikiCLIR