Knowledge-guided Open Attribute Value Extraction with Reinforcement Learning

TL;DR

This paper introduces a knowledge-guided reinforcement learning framework that leverages knowledge graphs to improve open attribute value extraction accuracy for emerging entities, outperforming existing methods significantly.

Contribution

It proposes a novel reinforcement learning approach guided by knowledge graphs to enhance attribute value extraction from noisy web data.

Findings

Outperforms baselines by 16.5-27.8% in accuracy

Effectively filters noisy articles and answers

Applicable to various information extraction systems

Abstract

Open attribute value extraction for emerging entities is an important but challenging task. A lot of previous works formulate the problem as a \textit{question-answering} (QA) task. While the collections of articles from web corpus provide updated information about the emerging entities, the retrieved texts can be noisy, irrelevant, thus leading to inaccurate answers. Effectively filtering out noisy articles as well as bad answers is the key to improving extraction accuracy. Knowledge graph (KG), which contains rich, well organized information about entities, provides a good resource to address the challenge. In this work, we propose a knowledge-guided reinforcement learning (RL) framework for open attribute value extraction. Informed by relevant knowledge in KG, we trained a deep Q-network to sequentially compare extracted answers to improve extraction accuracy. The proposed framework is applicable to different information extraction system. Our experimental results show that our method outperforms the baselines by 16.5 - 27.8\%.