Neural Machine Translation with Noisy Lexical Constraints
This addresses a practical issue for machine translation users where constraints may contain errors, though it is incremental as it builds on existing lexically constrained decoding methods.
The paper tackles the problem of handling noisy lexical constraints in neural machine translation by proposing a framework that treats constraints as external memories, allowing mistaken constraints to be corrected. Experiments show substantial BLEU gains with noisy constraints and improved translation quality with automatically generated constraints.
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.