Neural Machine Translation with Noisy Lexical Constraints
arXiv:1908.04664 · doi:10.1109/TASLP.2020.2999724
Abstract
Lexically constrained decoding for machine translation has shown to be beneficial in previous studies. Unfortunately, constraints provided by users may contain mistakes in real-world situations. It is still an open question that how to manipulate these noisy constraints in such practical scenarios. We present a novel framework that treats constraints as external memories. In this soft manner, a mistaken constraint can be corrected. Experiments demonstrate that our approach can achieve substantial BLEU gains in handling noisy constraints. These results motivate us to apply the proposed approach on a new scenario where constraints are generated without the help of users. Experiments show that our approach can indeed improve the translation quality with the automatically generated constraints.
arXiv commentThis paper was accepted by TASLP. See https://ieeexplore.ieee.org/document/9108255/ for the final version
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Efficient Estimation of Word Representations in Vector Space
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Convolutional Sequence to Sequence Learning
- Learning to Remember Rare Events
- Bridging Neural Machine Translation and Bilingual Dictionaries
- Code-Switching for Enhancing NMT with Pre-Specified Translation
- Search Engine Guided Non-Parametric Neural Machine Translation
- QuickEdit: Editing Text & Translations by Crossing Words Out
- Learning to Discriminate Noises for Incorporating External Information in Neural Machine Translation