Boundary Smoothing for Named Entity Recognition
Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous state-of-the-art systems on eight well-known NER benchmarks. Further empirical analysis suggests that boundary smoothing effectively mitigates over-confidence, improves model calibration, and brings flatter neural minima and more smoothed loss landscapes.
Code (1)
Tasks
Chinese Named Entity Recognitionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERNested Named Entity RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Boundary Smoothing for Named Entity Recognition
Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation …
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERIntegrating Boundary Assembling into a DNN Framework for Named Entity Recognition in Chinese Social Media Text
Named entity recognition is a challenging task in Natural Language Processing, especially for informal and noisy social media text. Chinese word boundaries are also entity boundaries, therefore, named entity recognition …
Boundary DetectionChinese Word Segmentationnamed-entity-recognitionNamed Entity Recognition+2A Boundary Offset Prediction Network for Named Entity Recognition
Named entity recognition (NER) is a fundamental task in natural language processing that aims to identify and classify named entities in text. However, span-based methods for NER typically assign entity types to text spa…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+1Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition
Named Entity Recognition (NER) is a well and widely studied task in natural language processing. Recently, the nested NER has attracted more attention since its practicality and difficulty. Existing works for nested NER …
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+4Boundary identification of events in clinical named entity recognition
The problem of named entity recognition in the medical/clinical domain has gained increasing attention do to its vital role in a wide range of clinical decision support applications. The identification of complete and co…
General Classificationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)