A Joint Model for Named Entity Recognition With Sentence-Level Entity Type Attentions

Named entity recognition (NER) is one fundamental task in natural language processing, which is typically addressed by neural condition random field (CRF) models, regarding the task as a sequence labeling problem. Sentence-level information has been shown positive for the task. Equipped with sophist...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/ACM transactions on audio, speech, and language processing speech, and language processing, 2021, Vol.29, p.1438-1448
Main Authors: Qian, Tao, Zhang, Meishan, Lou, Yinxia, Hua, Daiwen
Format: Article
Language:English
Subjects:
Bit error rate
Datasets
Fields (mathematics)
Joint model
Labeling
Learning
learning with auxiliary tasks
multi-task learning
named entity recognition
Natural language processing
Recognition
Semantics
Speech processing
Speech recognition
Task analysis
Training
Voice recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Named entity recognition (NER) is one fundamental task in natural language processing, which is typically addressed by neural condition random field (CRF) models, regarding the task as a sequence labeling problem. Sentence-level information has been shown positive for the task. Equipped with sophisticated neural structures such as long-short term memory network (LSTM), implicit sentence-level global information can be exploited fully, and has also been demonstrated effective in previous studies. In this work, we propose a new method for better learning of these sentence-level features in an explicit manner. Concretely, we suggest an auxiliary task, namely sentence-level named type prediction (i.e., determining whether a sentence includes a certain kind of named type), to supervise the feature representation learning globally. We conduct experiments on six benchmark datasets of various languages to evaluate our method. The results show that our final model is highly effective, resulting in significant improvements and leading to highly competitive results on all datasets.
ISSN:2329-9290
2329-9304
DOI:10.1109/TASLP.2021.3069295