Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing

About

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.

Chao Lou, Songlin Yang, Kewei Tu• 2022

Related benchmarks

TaskDatasetResultRank
Nested Named Entity RecognitionACE 2004 (test)
F1 Score87.9
166
Nested Named Entity RecognitionACE 2005 (test)
F1 Score86.91
153
Nested Named Entity RecognitionGENIA (test)
F1 Score78.44
140
Named Entity RecognitionACE04 (test)
F1 Score87.9
36
Named Entity RecognitionACE05 splits of Lu and Roth (test)
F1 Score86.91
14
Nested Named Entity RecognitionNNE
Precision94.32
2
Showing 6 of 6 rows

Other info

Code

Follow for update