NLP-CIC @ PRELEARN: Mastering prerequisites relations, from handcrafted\n features to embeddings

2020/11/07 by Jason Angel, Segun Taofeek Aroyehun, Angel, Jason +3
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Machine Learning in Healthcare #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2011.03760

openalex publication_date 2020/11/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present our systems and findings for the prerequisite relation learning\ntask (PRELEARN) at EVALITA 2020. The task aims to classify whether a pair of\nconcepts hold a prerequisite relation or not. We model the problem using\nhandcrafted features and embedding representations for in-domain and\ncross-domain scenarios. Our submissions ranked first place in both scenarios\nwith average F1 score of 0.887 and 0.690 respectively across domains on the\ntest sets. We made our code is freely available.\n

Related

• Inferring Concept Prerequisite Relations from Online Educational\n Resources
• ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning
• Finding Prerequisite Relations between Concepts using Textbook
• R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning
• What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning