Machine Translation for Machines: the Sentiment Classification Use Case

Amirhossein Tebbifakhr, Luisa Bentivogli, Matteo Negri, Marco Turchi


Abstract
We propose a neural machine translation (NMT) approach that, instead of pursuing adequacy and fluency (“human-oriented” quality criteria), aims to generate translations that are best suited as input to a natural language processing component designed for a specific downstream task (a “machine-oriented” criterion). Towards this objective, we present a reinforcement learning technique based on a new candidate sampling strategy, which exploits the results obtained on the downstream task as weak feedback. Experiments in sentiment classification of Twitter data in German and Italian show that feeding an English classifier with “machine-oriented” translations significantly improves its performance. Classification results outperform those obtained with translations produced by general-purpose NMT models as well as by an approach based on reinforcement learning. Moreover, our results on both languages approximate the classification accuracy computed on gold standard English tweets.
Anthology ID:
D19-1140
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1368–1374
Language:
URL:
https://www.aclweb.org/anthology/D19-1140
DOI:
10.18653/v1/D19-1140
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-1140.pdf