Predicting Prerequisite Relations for Unseen Concepts

Yaxin Zhu, Hamed Zamani


Abstract
Concept prerequisite learning (CPL) plays a key role in developing technologies that assist people to learn a new complex topic or concept. Previous work commonly assumes that all concepts are given at training time and solely focuses on predicting the unseen prerequisite relationships between them. However, many real-world scenarios deal with concepts that are left undiscovered at training time, which is relatively unexplored. This paper studies this problem and proposes a novel alternating knowledge distillation approach to take advantage of both content- and graph-based models for this task. Extensive experiments on three public benchmarks demonstrate up to 10% improvements in terms of F1 score.
Anthology ID:
2022.emnlp-main.585
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8542–8548
Language:
URL:
https://aclanthology.org/2022.emnlp-main.585
DOI:
10.18653/v1/2022.emnlp-main.585
Bibkey:
Cite (ACL):
Yaxin Zhu and Hamed Zamani. 2022. Predicting Prerequisite Relations for Unseen Concepts. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8542–8548, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Predicting Prerequisite Relations for Unseen Concepts (Zhu & Zamani, EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.585.pdf