Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification

Zhi-Xiu Ye, Zhen-Hua Ling


Abstract
This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification. Previous studies on this topic adopt prototypical networks, which calculate the embedding vector of a query instance and the prototype vector of the support set for each relation candidate independently. On the contrary, our proposed MLMAN model encodes the query instance and each support set in an interactive way by considering their matching information at both local and instance levels. The final class prototype for each support set is obtained by attentive aggregation over the representations of support instances, where the weights are calculated using the query instance. Experimental results demonstrate the effectiveness of our proposed methods, which achieve a new state-of-the-art performance on the FewRel dataset.
Anthology ID:
P19-1277
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2872–2881
Language:
URL:
https://aclanthology.org/P19-1277
DOI:
10.18653/v1/P19-1277
Bibkey:
Cite (ACL):
Zhi-Xiu Ye and Zhen-Hua Ling. 2019. Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2872–2881, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification (Ye & Ling, ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/P19-1277.pdf
Video:
 https://vimeo.com/384744882
Code
 ZhixiuYe/MLMAN
Data
FewRel