Text matching aims to establish the matching relationship between two texts. It is an important operation in some information retrieval related tasks such as question duplicate detection, question answer- ing, and dialog systems. Bidirectional long short term memory (BiLSTM) coupled with attention mechanism has achieved state-of- the-art performance in text matching. A major limitation of existing works is that only high level contextualized word representations are utilized to obtain word level matching results without consider- ing other levels of word representations, thus resulting in incorrect matching decisions for cases where two words with different mean- ings are very close in high level contextualized word representation space. Therefore, instead of making decisions utilizing single level word representations, a multi-level matching network (MMN) is proposed in this paper for text matching, which utilizes multiple lev- els of word representations to obtain multiple word level matching results for final text level matching decision. Experimental results on two widely used benchmarks, SNLI and Scaitail, show that the proposed MMN achieves the state-of-the-art performance.
|Title of host publication||SIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval|
|Number of pages||4|
|Publication status||Published - 18 Jul 2019|
- Multi-level matching network
- Text matching
- text matching
- multi-level matching network