| Autor: |
Arora, Jatin, Park, Youngja |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (2023) 416-426 |
| Druh dokumentu: |
Working Paper |
| DOI: |
10.18653/v1/2023.acl-short.36 |
| Popis: |
In this work, we address the NER problem by splitting it into two logical sub-tasks: (1) Span Detection which simply extracts entity mention spans irrespective of entity type; (2) Span Classification which classifies the spans into their entity types. Further, we formulate both sub-tasks as question-answering (QA) problems and produce two leaner models which can be optimized separately for each sub-task. Experiments with four cross-domain datasets demonstrate that this two-step approach is both effective and time efficient. Our system, SplitNER outperforms baselines on OntoNotes5.0, WNUT17 and a cybersecurity dataset and gives on-par performance on BioNLP13CG. In all cases, it achieves a significant reduction in training time compared to its QA baseline counterpart. The effectiveness of our system stems from fine-tuning the BERT model twice, separately for span detection and classification. The source code can be found at https://github.com/c3sr/split-ner. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
