Enwei Zhu, Jinpeng Li
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
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 stateof-the-art systems on eight well-known NER benchmarks. 1 Further empirical analysis suggests that boundary smoothing effectively mitigates over-confidence, improves model calibration, and brings flatter neural minima and more smoothed loss landscapes.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.12031")
get_code_for_paper("2204.12031")
have("2204.12031")
Connect an agent — have() is free.