Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions
Cuong Hoang, Devendra Sachan, Prashant Mathur, Brian Thompson, Marcello Federico
Abstract
We explore zero-shot adaptation, where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. We build on the idea of Retrieval Augmented Translation (RAT) where top-k in-domain fuzzy matches are found for the source sentence, and target-language translations of those fuzzy-matched sentences are provided to the translation model at inference time. We propose a novel architecture to control interactions between a source sentence and the top-k fuzzy target-language matches, and compare it to architectures from prior work. We conduct experiments in two language pairs (En-De and En-Fr) by training models on WMT data and testing them with five and seven multi-domain datasets, respectively. Our approach consistently outperforms the alternative architectures, improving BLEU across language pair, domain, and number k of fuzzy matches.- Anthology ID:
- 2023.findings-eacl.22
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 289–295
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.22
- DOI:
- 10.18653/v1/2023.findings-eacl.22
- Cite (ACL):
- Cuong Hoang, Devendra Sachan, Prashant Mathur, Brian Thompson, and Marcello Federico. 2023. Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions. In Findings of the Association for Computational Linguistics: EACL 2023, pages 289–295, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions (Hoang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-eacl.22.pdf