Nothing Special   »   [go: up one dir, main page]

GNN-SL: Sequence Labeling Based on Nearest Examples via GNN

Shuhe Wang, Yuxian Meng, Rongbin Ouyang, Jiwei Li, Tianwei Zhang, Lingjuan Lyu, Guoyin Wang


Abstract
To better handle long-tail cases in the sequence labeling (SL) task, in this work, we introduce graph neural networks sequence labeling (GNN-SL), which augments the vanilla SL model output with similar tagging examples retrieved from the whole training set. Since not all the retrieved tagging examples benefit the model prediction, we construct a heterogeneous graph, and leverage graph neural networks (GNNs) to transfer information between the retrieved tagging examples and the input word sequence. The augmented node which aggregates information from neighbors is used to do prediction. This strategy enables the model to directly acquire similar tagging examples and improves the general quality of predictions. We conduct a variety of experiments on three typical sequence labeling tasks: Named Entity Recognition (NER), Part of Speech Tagging (POS), and Chinese Word Segmentation (CWS) to show the significant performance of our GNN-SL. Notably, GNN-SL achieves SOTA results of 96.9 (+0.2) on PKU, 98.3 (+0.4) on CITYU, 98.5 (+0.2) on MSR, and 96.9 (+0.2) on AS for the CWS task, and resultscomparable to SOTA performances on NER datasets, and POS datasets.
Anthology ID:
2023.findings-acl.803
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12679–12692
Language:
URL:
https://aclanthology.org/2023.findings-acl.803
DOI:
10.18653/v1/2023.findings-acl.803
Bibkey:
Cite (ACL):
Shuhe Wang, Yuxian Meng, Rongbin Ouyang, Jiwei Li, Tianwei Zhang, Lingjuan Lyu, and Guoyin Wang. 2023. GNN-SL: Sequence Labeling Based on Nearest Examples via GNN. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12679–12692, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
GNN-SL: Sequence Labeling Based on Nearest Examples via GNN (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.803.pdf