Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings

2017/04/02 by Junki Matsuo, Matsuo, Junki, Mamoru Komachi +3
Computer Science · #Natural Language Processing Techniques #Semantic Web and Ontologies #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1704.00380

5 pages

arxiv created 2017/04/02 · arxiv updated 2017/04/04

Abstract

One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We propose to use word embeddings to perform word alignment for segment-level MT evaluation. We performed experiments with three types of alignment methods using word embeddings. We evaluated our proposed methods with various translation datasets. Experimental results show that our proposed methods outperform previous word embeddings-based methods.

Related

• Learning aligned embeddings for semi-supervised word translation using Maximum Mean Discrepancy
• SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
• Leveraging Neural Machine Translation for Word Alignment
• Word Alignment in the Era of Deep Learning: A Tutorial
• Saliency-driven Word Alignment Interpretation for Neural Machine Translation