Hierarchical Modeling of Label Dependency and Label Noise in Fine-grained Entity Typing

Hierarchical Modeling of Label Dependency and Label Noise in Fine-grained Entity Typing

Junshuang Wu, Richong Zhang, Yongyi Mao, Masoumeh Soflaei Shahrbabak, Jinpeng Huai

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 3950-3956. https://doi.org/10.24963/ijcai.2021/544

Fine-grained entity typing (FET) aims to annotate the entity mentions in a sentence with fine-grained type labels. It brings plentiful semantic information for many natural language processing tasks. Existing FET approaches apply hard attention to learn on the noisy labels, and ignore that those noises have structured hierarchical dependency. Despite their successes, these FET models are insufficient in modeling type hierarchy dependencies and handling label noises. In this paper, we directly tackle the structured noisy labels by combining a forward tree module and a backward tree module. Specifically, the forward tree formulates the informative walk that hierarchically represents the type distributions. The backward tree models the erroneous walk that learns the noise confusion matrix. Empirical studies on several benchmark data sets confirm the effectiveness of the proposed framework.
Keywords:
Natural Language Processing: Information Extraction
Natural Language Processing: Named Entities
Natural Language Processing: NLP Applications and Tools