Structured Alignment Networks for Matching Sentences

Yang Liu, Matt Gardner, Mirella Lapata


Abstract
Many tasks in natural language processing involve comparing two sentences to compute some notion of relevance, entailment, or similarity. Typically this comparison is done either at the word level or at the sentence level, with no attempt to leverage the inherent structure of the sentence. When sentence structure is used for comparison, it is obtained during a non-differentiable pre-processing step, leading to propagation of errors. We introduce a model of structured alignments between sentences, showing how to compare two sentences by matching their latent structures. Using a structured attention mechanism, our model matches candidate spans in the first sentence to candidate spans in the second sentence, simultaneously discovering the tree structure of each sentence. Our model is fully differentiable and trained only on the matching objective. We evaluate this model on two tasks, natural entailment detection and answer sentence selection, and find that modeling latent tree structures results in superior performance. Analysis of the learned sentence structures shows they can reflect some syntactic phenomena.
Anthology ID:
D18-1184
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1554–1564
Language:
URL:
https://aclanthology.org/D18-1184
DOI:
10.18653/v1/D18-1184
Bibkey:
Cite (ACL):
Yang Liu, Matt Gardner, and Mirella Lapata. 2018. Structured Alignment Networks for Matching Sentences. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1554–1564, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Structured Alignment Networks for Matching Sentences (Liu et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1184.pdf
Data
SNLITrecQA