Chatterjee, Soumya ; Sarawagi, Sunita ; Jyothi, Preethi (2022) Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding In: 60th Annual Meeting of the Association for Computational Linguistics.
PDF
424kB |
Official URL: https://doi.org/10.48550/arXiv.2204.00871
Related URL: http://dx.doi.org/10.48550/arXiv.2204.00871
Abstract
Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded. Good online alignments facilitate important applications such as lexically constrained translation where user-defined dictionaries are used to inject lexical constraints into the translation model. We propose a novel posterior alignment technique that is truly online in its execution and superior in terms of alignment error rates compared to existing methods. Our proposed inference technique jointly considers alignment and token probabilities in a principled manner and can be seamlessly integrated within existing constrained beam-search decoding algorithms. On five language pairs, including two distant language pairs, we achieve consistent drop in alignment error rates. When deployed on seven lexically constrained translation tasks, we achieve significant improvements in BLEU specifically around the constrained positions.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Source: | Copyright of this article belongs to Association for Computational Linguistics |
ID Code: | 128247 |
Deposited On: | 18 Oct 2022 10:44 |
Last Modified: | 15 Nov 2022 08:40 |
Repository Staff Only: item control page