A Neural Transition-based Model for Nested Mention Recognition

TL;DR

This paper presents a scalable neural transition-based model for nested mention recognition, effectively capturing recursive entity structures and achieving state-of-the-art results on ACE datasets.

Contribution

It introduces a novel shift-reduce, forest-based approach with Stack-LSTM and character-level features for nested mention detection.

Findings

Achieves state-of-the-art performance on ACE datasets.

Effectively models nested mentions with a bottom-up forest construction.

Utilizes character-based features for improved recognition.

Abstract

It is common that entity mentions can contain other mentions recursively. This paper introduces a scalable transition-based method to model the nested structure of mentions. We first map a sentence with nested mentions to a designated forest where each mention corresponds to a constituent of the forest. Our shift-reduce based system then learns to construct the forest structure in a bottom-up manner through an action sequence whose maximal length is guaranteed to be three times of the sentence length. Based on Stack-LSTM which is employed to efficiently and effectively represent the states of the system in a continuous space, our system is further incorporated with a character-based component to capture letter-level patterns. Our model achieves the state-of-the-art results on ACE datasets, showing its effectiveness in detecting nested mentions.