vix.ing · top · new · best · stats · spec

Code-Switching for Enhancing NMT with Pre-Specified Translation

2019/04/19 by Kai Song, Song, Kai, Yue Zhang +9 · 5 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1904.09107

openalex publication_date 2019/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during decoding. Both methods can hurt translation fidelity for various reasons. We investigate a data augmentation method, making code-switched training data by replacing source phrases with their target translations. Our method does not change the MNT model or decoding algorithm, allowing the model to learn lexicon translations by copying source-side target words. Extensive experiments show that our method achieves consistent improvements over existing approaches, improving translation of constrained words without hurting unconstrained words.

Citations

Cited by

Related