Improving word mover's distance by leveraging self-attention matrix

November 11, 2022 ยท Declared Dead ยท ๐Ÿ› Conference on Empirical Methods in Natural Language Processing

๐Ÿ’€ CAUSE OF DEATH: 404 Not Found
Code link is broken/dead
Authors Hiroaki Yamagiwa, Sho Yokoi, Hidetoshi Shimodaira arXiv ID 2211.06229 Category cs.CL: Computation & Language Citations 7 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/ymgw55/WSMD} Last Checked 1 month ago
Abstract
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}.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 8 years ago

Died the same way โ€” ๐Ÿ’€ 404 Not Found