Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing
This work addresses nested NER, a key challenge in natural language processing for extracting structured information from text, by introducing a novel parsing-based method that leverages entity heads, representing an incremental improvement over prior span-based approaches.
The paper tackles nested named entity recognition by modeling entities as lexicalized constituency trees with headwords, achieving state-of-the-art performance on ACE2004, ACE2005, and NNE datasets, with competitive results on GENIA and fast inference speed.
Nested named entity recognition (NER) has been receiving increasing attention. Recently, (Fu et al, 2021) adapt a span-based constituency parser to tackle nested NER. They treat nested entities as partially-observed constituency trees and propose the masked inside algorithm for partial marginalization. However, their method cannot leverage entity heads, which have been shown useful in entity mention detection and entity typing. In this work, we resort to more expressive structures, lexicalized constituency trees in which constituents are annotated by headwords, to model nested entities. We leverage the Eisner-Satta algorithm to perform partial marginalization and inference efficiently. In addition, we propose to use (1) a two-stage strategy (2) a head regularization loss and (3) a head-aware labeling loss in order to enhance the performance. We make a thorough ablation study to investigate the functionality of each component. Experimentally, our method achieves the state-of-the-art performance on ACE2004, ACE2005 and NNE, and competitive performance on GENIA, and meanwhile has a fast inference speed.