Word Alignment by Fine-tuning Embeddings on Parallel Corpora

By Zi-Yi Dou, Graham Neubig. Conference of the European Chapter of the Association for Computational Linguistics, 2021

323 citations recorded by the source corpus.

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great majority of past work on word alignment has worked by performing unsupervised learning on parallel text. Recently, however, other work has demonstrated that pre-trained contextualized word embeddings derived from multilingually trained language models (LMs) prove an attractive alternative, achieving competitive results on the word alignment task even in the absence of explicit training on parallel data. In this paper, we examine methods to marry the two approaches: leveraging pre-trained LMs but fine-tuning them on parallel text with objectives designed to improve alignment quality, and proposing methods to effectively extract alignments from these fine-tuned models. We perform experiments on five language pairs and demonstrate that our model can consistently outperform previous state-of-the-art models of all varieties. In addition, we demonstrate that we are able to train multilingual word aligners that can obtain robust performance on different language pairs.

View Paper: https://www.semanticscholar.org/paper/821532ecef5bc2252823b190c35f1e4c44ddc41c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation (2023, methodology): “For obtaining word to word alignments, we use a multilingual-bert based aligner (Devlin et al., 2019; Dou and Neubig, 2021).”