This paper has been retracted. The authors discovered a problem with the experiments, whose correction unfortunately changes the findings of the paper.
Abstract
Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated into NMT. In this paper, we describe a new method for “attaching” dictionary definitions to rare words so that the network can learn the best way to use them. We demonstrate improvements of up to 3.1 BLEU using bilingual dictionaries and up to 0.7 BLEU using monolingual source-language dictionaries.- Anthology ID:
- 2020.wmt-1.65
- Original:
- 2020.wmt-1.65v1
- Version 2:
- 2020.wmt-1.65v2
- Volume:
- Proceedings of the Fifth Conference on Machine Translation
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Yvette Graham, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 538–549
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.65
- DOI:
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2020.wmt-1.65.pdf