Neural Machine Translation Decoding with Terminology Constraints

Conference Object
Change log
Hasler, eva 
de Gspert, Adrià 
Iglesias, Gonzalo 
Byrne, WJ 

Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology con- straints remains an open problem. We describe our approach to constrained neural decod- ing based on finite-state machines and multi- stack decoding which supports target-side con- straints as well as constraints with correspond- ing aligned input text spans. We demonstrate the performance of our framework on multiple translation tasks and motivate the need for constrained decoding with attentions as a means of reducing misplacement and duplication when translating user constraints.

Journal Title
Conference Name
16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Journal ISSN
Volume Title
Association for Computational Linguistics
Engineering and Physical Sciences Research Council (EP/L027623/1)