Joint entity recognition and relation extraction as a multi-head selection problem

TL;DR

This paper introduces a neural model that jointly performs entity recognition and relation extraction without external NLP tools, achieving superior results across diverse datasets and languages.

Contribution

The proposed model eliminates the need for external NLP features by integrating entity recognition and relation extraction into a unified neural framework.

Findings

Outperforms previous neural models using automatic features

Achieves competitive results with feature-based neural models

Effective across multiple languages and domains

Abstract

State-of-the-art models for joint entity recognition and relation extraction strongly rely on external natural language processing (NLP) tools such as POS (part-of-speech) taggers and dependency parsers. Thus, the performance of such joint models depends on the quality of the features obtained from these NLP tools. However, these features are not always accurate for various languages and contexts. In this paper, we propose a joint neural model which performs entity recognition and relation extraction simultaneously, without the need of any manually extracted features or the use of any external tool. Specifically, we model the entity recognition task using a CRF (Conditional Random Fields) layer and the relation extraction task as a multi-head selection problem (i.e., potentially identify multiple relations for each entity). We present an extensive experimental setup, to demonstrate the effectiveness of our method using datasets from various contexts (i.e., news, biomedical, real estate) and languages (i.e., English, Dutch). Our model outperforms the previous neural models that use automatically extracted features, while it performs within a reasonable margin of feature-based neural models, or even beats them.