Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications
Jatin Arora, Youngja H. Park · 2023
In this work, we address the NER problem by splitting it into two logical sub-tasks: (1) Span Detection which simply extracts mention spans of entities, 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 crossdomain 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 github.com/c3sr/split-ner.