Journal
INFORMATION PROCESSING & MANAGEMENT
Volume 60, Issue 4, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.ipm.2023.103352
Keywords
Named entity recognition; Sentence representation; Self-cross encoding; Planarized sentence representation
Ask authors/readers for more resources
This paper proposes a strategy to recognize nested entities by enumerating overlapped entity spans for classification. Then, a bi-directional two-dimensional recurrent operation is used to learn semantic dependencies between spans. Experimental results show that the proposed method is effective in resolving nested named entities and learning semantic dependencies between them.
One strategy to recognize nested entities is to enumerate overlapped entity spans for classi-fication. However, current models independently verify every entity span, which ignores the semantic dependency between spans. In this paper, we first propose a planarized sentence representation to represent nested named entities. Then, a bi-directional two-dimensional recurrent operation is implemented to learn semantic dependencies between spans. Our method is evaluated on seven public datasets for named entity recognition. It achieves competitive performance in named entity recognition. The experimental results show that our method is effective to resolve nested named entities and learn semantic dependencies between them.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available