Improving slot filling performance with attentive neural networks on dependency structures

Lifu Huang, Avirup Sil, Heng Ji, Radu Florian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities of residence) for a given entity from a large collection of source documents. In this paper we propose an effective DNN architecture for SF with the following new strategies: (1). Take a regularized dependency graph instead of a raw sentence as input to DNN, to compress the wide contexts between query and candidate filler; (2). Incorporate two attention mechanisms: local attention learned from query and candidate filler, and global attention learned from external knowledge bases, to guide the model to better select indicative contexts to determine slot type. Experiments show that this framework outperforms state-of-the-art on both relation extraction (16% absolute F-score gain) and slot filling validation for each individual system (up to 8.5% absolute F-score gain).

Original languageEnglish (US)
Title of host publicationEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages2588-2597
Number of pages10
ISBN (Electronic)9781945626838
DOIs
StatePublished - Jan 1 2017
Externally publishedYes
Event2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark
Duration: Sep 9 2017Sep 11 2017

Publication series

NameEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Country/TerritoryDenmark
CityCopenhagen
Period9/9/179/11/17

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Improving slot filling performance with attentive neural networks on dependency structures'. Together they form a unique fingerprint.

Cite this