End-to-End Relation Extraction using Markov Logic Networks

TL;DR

This paper presents a novel end-to-end relation extraction method that jointly identifies entities and their relations using Markov Logic Networks, improving over previous approaches on the ACE 2004 dataset.

Contribution

It introduces a joint inference approach with MLNs that combines multiple classifiers and domain knowledge for more consistent relation extraction.

Findings

Outperforms baseline classifiers in relation extraction accuracy.

Achieves better results than 2 out of 3 previous methods on ACE 2004.

Demonstrates the effectiveness of joint inference with MLNs.

Abstract

The task of end-to-end relation extraction consists of two sub-tasks: i) identifying entity mentions along with their types and ii) recognizing semantic relations among the entity mention pairs. %Identifying entity mentions along with their types and recognizing semantic relations among the entity mentions, are two very important problems in Information Extraction. It has been shown that for better performance, it is necessary to address these two sub-tasks jointly. We propose an approach for simultaneous extraction of entity mentions and relations in a sentence, by using inference in Markov Logic Networks (MLN). We learn three different classifiers : i) local entity classifier, ii) local relation classifier and iii) "pipeline" relation classifier which uses predictions of the local entity classifier. Predictions of these classifiers may be inconsistent with each other. We represent these predictions along with some domain knowledge using weighted first-order logic rules in an MLN and perform joint inference over the MLN to obtain a global output with minimum inconsistencies. Experiments on the ACE (Automatic Content Extraction) 2004 dataset demonstrate that our approach of joint extraction using MLNs outperforms the baselines of individual classifiers. Our end-to-end relation extraction performance is better than 2 out of 3 previous results reported on the ACE 2004 dataset.