Work

SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition

Year: 2023

Type: conference-paper

Abstract: Distantly-Supervised Named Entity Recognition effectively alleviates the burden of timeconsuming and expensive annotation in the supervised setting.But the context-free matching process and the limited coverage of knowledge bases introduce inaccurate and incomplete annotation noise respectively.Previous studies either considered only incomplete annotation noise or indiscriminately handle two types of noise with the same strategy.In this paper, we argue that the different causes of two types of noise bring up the requirement of different strategies in model architecture.Therefore, we propose the SANTA to handle these two types of noise separately with (1) Memory-smoothed Focal Loss and Entity-aware KNN to relieve the entity ambiguity problem caused by inaccurate annotation, and (2) Boundary Mixup to alleviate decision boundary shifting problem caused by incomplete annotation and a noisetolerant loss to improve the robustness.Benefiting from our separate tailored strategies, we confirm in the experiment that the two types of noise are well mitigated.SANTA also achieves a new state-of-the-art on five public datasets.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2023.findings-acl.239

Authors: Shuzheng Si, Zefan Cai, Shuang Zeng, Guoqiang Feng, Jiaxing Lin, Baobao Chang

Institution: Peking University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Natural Science Foundation of China

Award: 基于语言认知机理的汉语框架语义计算研究