Dependency-Guided LSTM-CRF for Named Entity Recognition

TL;DR

This paper introduces a dependency-guided LSTM-CRF model that leverages dependency tree structures to improve named entity recognition by capturing long-distance syntactic relations, achieving state-of-the-art results.

Contribution

The paper proposes a novel dependency-guided LSTM-CRF model that encodes dependency trees to enhance NER performance, demonstrating significant improvements over existing methods.

Findings

The model achieves state-of-the-art NER performance on standard datasets.

Dependency relations and long-distance interactions significantly improve recognition accuracy.

Strong correlations exist between entity types and dependency relations.

Abstract

Dependency tree structures capture long-distance and syntactic relationships between words in a sentence. The syntactic relations (e.g., nominal subject, object) can potentially infer the existence of certain named entities. In addition, the performance of a named entity recognizer could benefit from the long-distance dependencies between the words in dependency trees. In this work, we propose a simple yet effective dependency-guided LSTM-CRF model to encode the complete dependency trees and capture the above properties for the task of named entity recognition (NER). The data statistics show strong correlations between the entity types and dependency relations. We conduct extensive experiments on several standard datasets and demonstrate the effectiveness of the proposed model in improving NER and achieving state-of-the-art performance. Our analysis reveals that the significant improvements mainly result from the dependency relations and long-distance interactions provided by dependency trees.