TY - GEN
T1 - Improving slot filling performance with attentive neural networks on dependency structures
AU - Huang, Lifu
AU - Sil, Avirup
AU - Ji, Heng
AU - Florian, Radu
N1 - Funding Information:
This work was supported by the DARPA DEFT No. FA8750-13-2-0041, U.S. ARL NS-CTA No. W911NF-09-2-0053, and NSF IIS 1523198. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.
Publisher Copyright:
© 2017 Association for Computational Linguistics.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2017/1/1
Y1 - 2017/1/1
N2 - 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).
AB - 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).
UR - http://www.scopus.com/inward/record.url?scp=85053724760&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85053724760&partnerID=8YFLogxK
U2 - 10.18653/v1/d17-1274
DO - 10.18653/v1/d17-1274
M3 - Conference contribution
T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 2588
EP - 2597
BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Y2 - 9 September 2017 through 11 September 2017
ER -