Neural Machine Translation Decoding with Terminology Constraints
This addresses the need for more reliable and user-controllable translation systems, though it is incremental as it builds on existing constrained decoding methods.
The paper tackles the problem of controlling neural machine translation output to adhere to user-provided terminology constraints, demonstrating a framework based on finite-state machines and multi-stack decoding that reduces misplacement and duplication of constraints.
Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to constrained neural decoding based on finite-state machines and multi-stack decoding which supports target-side constraints as well as constraints with corresponding 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.