Generic and Trend-aware Curriculum Learning for Relation Extraction

Nidhi Vakil, Hadi Amiri


Abstract
We present a generic and trend-aware curriculum learning approach that effectively integrates textual and structural information in text graphs for relation extraction between entities, which we consider as node pairs in graphs. The proposed model extends existing curriculum learning approaches by incorporating sample-level loss trends to better discriminate easier from harder samples and schedule them for training. The model results in a robust estimation of sample difficulty and shows sizable improvement over the state-of-the-art approaches across several datasets.
Anthology ID:
2022.naacl-main.160
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2202–2213
Language:
URL:
https://aclanthology.org/2022.naacl-main.160
DOI:
10.18653/v1/2022.naacl-main.160
Bibkey:
Cite (ACL):
Nidhi Vakil and Hadi Amiri. 2022. Generic and Trend-aware Curriculum Learning for Relation Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2202–2213, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Generic and Trend-aware Curriculum Learning for Relation Extraction (Vakil & Amiri, NAACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2022.naacl-main.160.pdf
Video:
 https://preview.aclanthology.org/emnlp-22-attachments/2022.naacl-main.160.mp4