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

Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks

About

Sequential labeling-based NER approaches restrict each word belonging to at most one entity mention, which will face a serious problem when recognizing nested entity mentions. In this paper, we propose to resolve this problem by modeling and leveraging the head-driven phrase structures of entity mentions, i.e., although a mention can nest other mentions, they will not share the same head word. Specifically, we propose Anchor-Region Networks (ARNs), a sequence-to-nuggets architecture for nested mention detection. ARNs first identify anchor words (i.e., possible head words) of all mentions, and then recognize the mention boundaries for each anchor word by exploiting regular phrase structures. Furthermore, we also design Bag Loss, an objective function which can train ARNs in an end-to-end manner without using any anchor word annotation. Experiments show that ARNs achieve the state-of-the-art performance on three standard nested entity mention detection benchmarks.

Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun• 2019

Related benchmarks

TaskDatasetResultRank
Nested Named Entity RecognitionACE 2004 (test)
F1 Score74.9
166
Nested Named Entity RecognitionACE 2005 (test)
F1 Score74.9
153
Nested Named Entity RecognitionGENIA (test)
F1 Score74.8
140
Named Entity RecognitionACE 2005 (test)
F1 Score74.9
58
Nested Named Entity RecognitionGENIA
F1 Score74.8
56
Nested Named Entity RecognitionACE 2005
F1 Score74.9
52
Named Entity RecognitionGENIA (test)
F1 Score74.8
34
Nested Mention DetectionACE2005 (test)
F1 Score74.9
30
Nested Named Entity RecognitionKBP English 2017 (test)
Precision77.7
28
Nested Mention DetectionGENIA (test)
Precision75.8
11
Showing 10 of 15 rows

Other info

Code

Follow for update