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

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

doi:10.24963/ijcai.2021/544

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

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

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3950-3956.

https://doi.org/10.24963/ijcai.2021/544

Keywords

Natural Language Processing: Named Entities
Natural Language Processing: Information Extraction
Natural Language Processing: NLP Applications and Tools

Abstract

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.

Junshuang Wu, Richong Zhang, Yongyi Mao, Masoumeh Soflaei Shahrbabak, and Jinpeng Huai. 2021. Hierarchical Modeling of Label Dependency and Label Noise in Fine-grained Entity Typing. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3950–3956. https://doi.org/10.24963/ijcai.2021/544

@inproceedings{ijcai2021p544,
  title     = {Hierarchical Modeling of Label Dependency and Label Noise in Fine-grained Entity Typing},
  author    = {Wu, Junshuang and Zhang, Richong and Mao, Yongyi and Soflaei Shahrbabak, Masoumeh and Huai, Jinpeng},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {3950--3956},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/544},
  url       = {https://doi.org/10.24963/ijcai.2021/544},
}

TY  - CPAPER
TI  - Hierarchical Modeling of Label Dependency and Label Noise in Fine-grained Entity Typing
AU  - Wu, Junshuang
AU  - Zhang, Richong
AU  - Mao, Yongyi
AU  - Soflaei Shahrbabak, Masoumeh
AU  - Huai, Jinpeng
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 3950
EP  - 3956
DO  - 10.24963/ijcai.2021/544
UR  - https://doi.org/10.24963/ijcai.2021/544
ER  -