A novel locality-sensitive hashing relational graph matching network for semantic textual similarity measurement

作者：

Highlights：

• Semantic textual similarity measurement depends on the syntax.

• Pruned syntactic dependency graph performs better than original tree.

• The most expensive part of inference time is the interactions of words.

• Locality-sensitive hashing mechanism is introduced into interactions of words.

• LSHRGMN both encodes the syntactic dependency graph and interactions of words.

摘要

•Semantic textual similarity measurement depends on the syntax.•Pruned syntactic dependency graph performs better than original tree.•The most expensive part of inference time is the interactions of words.•Locality-sensitive hashing mechanism is introduced into interactions of words.•LSHRGMN both encodes the syntactic dependency graph and interactions of words.

论文关键词：Semantic textual similarity,Graph neural network,Natural language processing,Deep learning

论文评审过程：Received 20 December 2021, Revised 7 June 2022, Accepted 8 June 2022, Available online 11 June 2022, Version of Record 2 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117832