Element-wise Bilinear Interaction for Sentence Matching

Jihun Choi, Taeuk Kim, Sang-goo Lee


Abstract
When we build a neural network model predicting the relationship between two sentences, the most general and intuitive approach is to use a Siamese architecture, where the sentence vectors obtained from a shared encoder is given as input to a classifier. For the classifier to work effectively, it is important to extract appropriate features from the two vectors and feed them as input. There exist several previous works that suggest heuristic-based function for matching sentence vectors, however it cannot be said that the heuristics tailored for a specific task generalize to other tasks. In this work, we propose a new matching function, ElBiS, that learns to model element-wise interaction between two vectors. From experiments, we empirically demonstrate that the proposed ElBiS matching function outperforms the concatenation-based or heuristic-based matching functions on natural language inference and paraphrase identification, while maintaining the fused representation compact.
Anthology ID:
S18-2012
Volume:
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Malvina Nissim, Jonathan Berant, Alessandro Lenci
Venue:
*SEM
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
107–112
Language:
URL:
https://aclanthology.org/S18-2012
DOI:
10.18653/v1/S18-2012
Bibkey:
Cite (ACL):
Jihun Choi, Taeuk Kim, and Sang-goo Lee. 2018. Element-wise Bilinear Interaction for Sentence Matching. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pages 107–112, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Element-wise Bilinear Interaction for Sentence Matching (Choi et al., *SEM 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/S18-2012.pdf
Data
SNLI