Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
Name
rlie16.pdf
Size
389.35 KB
Format
Adobe PDF
Checksum (MD5)
335ec8ce5d75a0e42c7ca963f8812b27
Author(s)
Narasimhan, Karthik Rajagopal
Yala, Adam
Barzilay, Regina
Date Issued
November 2016
Journal
Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP 2016
Publisher
Association for Computational Linguistics (ACL)
Citation
Narasimhan, Karthik, Adam Yala, and Regina Barzilay. "Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning." In EMNLP 2016: Conference on Empirical Methods in Natural Language Processing, November 1-5, 2016, Austin, Texas, USA.
Version
Author's final manuscript
Abstract
Most successful information extraction systems operate with access to a large collection of documents. In this work, we explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the amount of training data is scarce. This process entails issuing search queries, extraction from new sources and reconciliation of extracted values, which are repeated until sufficient evidence is collected. We approach the problem using a reinforcement learning framework where our model learns to select optimal actions based on contextual information. We employ a deep Qnetwork, trained to optimize a reward function that reflects extraction accuracy while penalizing extra effort. Our experiments on two databases--of shooting incidents, and food adulteration cases--demonstrate that our system significantly outperforms traditional extractors and a competitive meta-classifier baseline.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.emnlp2016.net/accepted-papers.html
