Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction

by   Gyubok Lee, et al.

Generating accurate terminology is a crucial component for the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases to appear in the translations. In many cases, however, those methods are evaluated on general domain corpora, where the terms are mostly uni- and bi-grams (>98 setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. To encourage span-level representations in generation, we additionally impose a source-sentence conditioned masked span prediction loss in the decoder and observe improvements on both terminology translation as well as BLEU scores. Experimental results on three domain-specific corpora in two language pairs demonstrate that the proposed training scheme can improve the performance of existing lexically constrained methods that can operate both with or without a term dictionary at test time.


page 1

page 2

page 3

page 4


Incorporating Discrete Translation Lexicons into Neural Machine Translation

Neural machine translation (NMT) often makes mistakes in translating low...

Multi-Source Neural Machine Translation with Missing Data

Multi-source translation is an approach to exploit multiple inputs (e.g....

Capturing document context inside sentence-level neural machine translation models with self-training

Neural machine translation (NMT) has arguably achieved human level parit...

Sentence Alignment with Parallel Documents Helps Biomedical Machine Translation

The existing neural machine translation system has achieved near human-l...

Bi-Decoder Augmented Network for Neural Machine Translation

Neural Machine Translation (NMT) has become a popular technology in rece...

When and Why are Pre-trainedWord Embeddings Useful for Neural Machine Translation?

The performance of Neural Machine Translation (NMT) systems often suffer...

Code-Switching for Enhancing NMT with Pre-Specified Translation

Leveraging user-provided translation to constrain NMT has practical sign...