Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings
This work addresses a key challenge in machine translation evaluation for researchers and practitioners, but it is incremental as it builds on existing word embeddings methods.
The paper tackled the problem of evaluating machine translation at the segment level when translations differ in surface form from the reference, by using word embeddings for word alignment. The proposed methods outperformed previous word embeddings-based approaches in experiments on various datasets.
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.