A Neural Transition-based Model for Nested Mention Recognition
This addresses the challenge of nested mention recognition in natural language processing, which is important for tasks like information extraction, but the approach is incremental as it builds on existing transition-based and neural methods.
The paper tackles the problem of recognizing nested entity mentions by introducing a scalable transition-based method that maps sentences to forests and uses a shift-reduce system with Stack-LSTM and character-based components. It achieves state-of-the-art results on ACE datasets, demonstrating effectiveness in detecting nested mentions.
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.