Improving word mover's distance by leveraging self-attention matrix
This work addresses a specific limitation in sentence similarity measurement for NLP applications, representing an incremental improvement over existing methods.
The authors tackled the problem of measuring semantic similarity between sentences by improving Word Mover's Distance (WMD) to incorporate word order using BERT's self-attention matrix, resulting in enhanced performance in paraphrase identification with near-equivalent results in semantic textual similarity.
Measuring the semantic similarity between two sentences is still an important task. The word mover's distance (WMD) computes the similarity via the optimal alignment between the sets of word embeddings. However, WMD does not utilize word order, making it challenging to distinguish sentences with significant overlaps of similar words, even if they are semantically very different. Here, we attempt to improve WMD by incorporating the sentence structure represented by BERT's self-attention matrix (SAM). The proposed method is based on the Fused Gromov-Wasserstein distance, which simultaneously considers the similarity of the word embedding and the SAM for calculating the optimal transport between two sentences. Experiments demonstrate the proposed method enhances WMD and its variants in paraphrase identification with near-equivalent performance in semantic textual similarity. Our code is available at \url{https://github.com/ymgw55/WSMD}.