Neural Open Information Extraction

Lei Cui,Furu Wei,Ming Zhou

doi:10.18653/v1/p18-2065

Abstract

Conventional Open Information Extraction (Open IE) systems are usually built on hand-crafted patterns from other NLP tools such as syntactic parsing, yet they face problems of error propagation. In this paper, we propose a neural Open IE approach with an encoder-decoder framework. Distinct from existing methods, the neural Open IE approach learns highly confident arguments and relation tuples bootstrapped from a state-of-the-art Open IE system. An empirical study on a large benchmark dataset shows that the neural Open IE system significantly outperforms several baselines, while maintaining comparable computational efficiency.

Highlights

Open Information Extraction (Open IE) involves generating a structured representation of information in text, usually in the form of triples or n-ary propositions
It is observed that the neural Open IE system performs best among all tested systems
We calculated the Area under Precision-Recall Curve (AUC) for each system

Summary

Introduction

Open Information Extraction (Open IE) involves generating a structured representation of information in text, usually in the form of triples or n-ary propositions. The Open IE system was first introduced by TEXTRUNNER (Banko et al, 2007), followed by several popular systems such as REVERB (Fader et al, 2011), OLLIE (Mausam et al, 2012), ClausIE (Del Corro and Gemulla, 2013) Stanford OPENIE (Angeli et al, 2015), PropS (Stanovsky et al, 2016) and most recently OPENIE41 (Mausam, 2016) and OPENIE52 These systems have been widely used in a variety of applications, most of them were built on hand-crafted patterns from syntactic parsing, which causes errors in propagation and compounding at each stage (Banko et al, 2007; Gashteovski et al, 2017; Schneider et al, 2017). It is essential to solve the problems of cascading errors to alleviate extracting incorrect tuples

Methods

Results

Conclusion