Designing an adaptive attention mechanism for relation classification

Entity pair provide essential information for identifying relation type. Aiming at this characteristic, Position Feature is widely used in current relation classification systems to highlight the words close to them. However, semantic knowledge involved in entity pair has not been fully utilized. To...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengda Qin, Weiran Xu, Jun Guo
Format: Conference Proceeding
Language:English
Subjects:
Feature extraction
Logic gates
Machine learning
Natural language processing
Neural networks
Pragmatics
Semantics
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Entity pair provide essential information for identifying relation type. Aiming at this characteristic, Position Feature is widely used in current relation classification systems to highlight the words close to them. However, semantic knowledge involved in entity pair has not been fully utilized. To overcome this issue, we propose an Entity-pair-based Attention Mechanism, which is specially designed for relation classification. Recently, attention mechanism significantly promotes the development of deep learning in NLP. Inspired by this, for specific instance(entity pair, sentence), the corresponding entity pair information is incorporated as prior knowledge to adaptively compute attention weights for generating sentence representation. Experimental results on SemEval-2010 Task 8 dataset show that our method outperforms most of the state-of-the-art models, without external linguistic features.
ISSN:2161-4407
DOI:10.1109/IJCNN.2017.7966407