Disambiguated Lexically Constrained Neural Machine Translation
This work improves LCNMT for practical applications where source lexicons have multiple target constraints, though it is incremental as it builds on existing LCNMT methods.
The paper tackled the problem of lexically constrained neural machine translation (LCNMT) by addressing the assumption that pre-specified constraints are contextually appropriate, proposing a two-stage framework called D-LCNMT that disambiguates constraints based on context and integrates them into LCNMT, resulting in outperformance of strong baselines on benchmark datasets.
Lexically constrained neural machine translation (LCNMT), which controls the translation generation with pre-specified constraints, is important in many practical applications. Current approaches to LCNMT typically assume that the pre-specified lexical constraints are contextually appropriate. This assumption limits their application to real-world scenarios where a source lexicon may have multiple target constraints, and disambiguation is needed to select the most suitable one. In this paper, we propose disambiguated LCNMT (D-LCNMT) to solve the problem. D-LCNMT is a robust and effective two-stage framework that disambiguates the constraints based on contexts at first, then integrates the disambiguated constraints into LCNMT. Experimental results show that our approach outperforms strong baselines including existing data augmentation based approaches on benchmark datasets, and comprehensive experiments in scenarios where a source lexicon corresponds to multiple target constraints demonstrate the constraint disambiguation superiority of our approach.