Query-Based Named Entity Recognition

Abstract

In this paper, we propose a new strategy for the task of named entity recognition (NER). We cast the task as a query-based machine reading comprehension task: e.g., the task of extracting entities with PER is formalized as answering the question of "which person is mentioned in the text ?". Such a strategy comes with the advantage that it solves the long-standing issue of handling overlapping or nested entities (the same token that participates in more than one entity categories) with sequence-labeling techniques for NER. Additionally, since the query encodes informative prior knowledge, this strategy facilitates the process of entity extraction, leading to better performances. We experiment the proposed model on five widely used NER datasets on English and Chinese, including MSRA, Resume, OntoNotes, ACE04 and ACE05. The proposed model sets new SOTA results on all of these datasets.

arXiv commentPlease refer to the full version of this paper: A unified framework for named entity recognition arXiv:1910.11476

References in corpus (14)

• Natural Language Processing (almost) from Scratch
• Bidirectional Attention Flow for Machine Comprehension
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Dynamic Coattention Networks For Question Answering
• Machine Comprehension Using Match-LSTM and Answer Pointer
• The Natural Language Decathlon: Multitask Learning as Question Answering
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Glyce: Glyph-vectors for Chinese Character Representations
• Multi-Perspective Context Matching for Machine Comprehension
• Reading Wikipedia to Answer Open-Domain Questions
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
• Chinese NER Using Lattice LSTM
• Neural Segmental Hypergraphs for Overlapping Mention Recognition
• A Neural Transition-based Model for Nested Mention Recognition