Reducing Spurious Correlations for Relation Extraction by Feature Decomposition and Semantic Augmentation-Reference-Cited by-同舟云学术

Reducing Spurious Correlations for Relation Extraction by Feature Decomposition and Semantic Augmentation

Published:2023-07-18 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
language:
Short-container-title:

Author:

Yu Tianshu¹^ORCID,Yang Min¹^ORCID,Li Chengming²^ORCID,Xu Ruifeng³^ORCID

Affiliation:

1. SIAT, Chinese Academy of Sciences, Shenzhen, China

2. Shenzhen MSU-BIT University, Shenzhen, China

3. Harbin Institute of Technology (Shenzhen), Shenzhen, China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3539618.3592050

Reference29 articles.

1. Freebase

2. Relation Extraction with Type-aware Map Memories of Word Dependencies

3. Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).

4. Ning Ding , Xiaobin Wang , Yao Fu , Guangwei Xu , Rui Wang , Pengjun Xie , Ying Shen , Fei Huang , Hai-Tao Zheng , and Rui Zhang . 2021. Prototypical representation learning for relation extraction. arXiv preprint arXiv:2103.11647 ( 2021 ). Ning Ding, Xiaobin Wang, Yao Fu, Guangwei Xu, Rui Wang, Pengjun Xie, Ying Shen, Fei Huang, Hai-Tao Zheng, and Rui Zhang. 2021. Prototypical representation learning for relation extraction. arXiv preprint arXiv:2103.11647 (2021).

5. Shihan Dou , Rui Zheng , Ting Wu , Songyang Gao , Qi Zhang , Yueming Wu , and Xuanjing Huang . 2022. Decorrelate Irrelevant , Purify Relevant : Overcome Textual Spurious Correlations from a Feature Perspective . arXiv preprint arXiv:2202.08048 ( 2022 ). Shihan Dou, Rui Zheng, Ting Wu, Songyang Gao, Qi Zhang, Yueming Wu, and Xuanjing Huang. 2022. Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective. arXiv preprint arXiv:2202.08048 (2022).