A Neural Transition-based Model for Nested Mention Recognition
It is common that entity mentions can contain other mentions recursively. This paper introduces a scalable transition-based method to model the nested structure of mentions. We first map a sentence with nested mentions to a designated forest where each mention corresponds to a constituent of the forest. Our shift-reduce based system then learns to construct the forest structure in a bottom-up manner through an action sequence whose maximal length is guaranteed to be three times of the sentence length. Based on Stack-LSTM which is employed to efficiently and effectively represent the states of the system in a continuous space, our system is further incorporated with a character-based component to capture letter-level patterns. Our model achieves the state-of-the-art results on ACE datasets, showing its effectiveness in detecting nested mentions.
PDF Abstract EMNLP 2018 PDF EMNLP 2018 AbstractCode
GENIA
ACE 2005
NNE
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Nested Mention Recognition | ACE 2004 | Neural transition-based model | F1 | 73.1 | # 7 | |
| Nested Named Entity Recognition | ACE 2004 | Neural transition-based model | F1 | 73.3 | # 23 | |
| Named Entity Recognition (NER) | ACE 2004 | Neural transition-based model | F1 | 73.3 | # 9 | |
| Multi-Task Supervision | n | # 1 | ||||
| Nested Named Entity Recognition | ACE 2005 | neural transition-based model | F1 | 73.0 | # 23 | |
| Nested Mention Recognition | ACE 2005 | Neural transition-based model | F1 | 73.0 | # 9 | |
| Named Entity Recognition (NER) | ACE 2005 | Neural transition-based model | F1 | 73.0 | # 19 | |
| Named Entity Recognition (NER) | GENIA | Neural transition-based model | F1 | 73.9 | # 13 | |
| Nested Named Entity Recognition | GENIA | Neural transition-based model | F1 | 73.9 | # 25 |
