A Transfer Learning Pipeline for Educational Resource Discovery with Application in Leading Paragraph Generation

TL;DR

This paper introduces a transfer learning pipeline for discovering educational resources across new domains, utilizing a novel neural network model for feature extraction, and demonstrates its application in generating leading paragraphs for surveys.

Contribution

It presents a new ERD pipeline with a pretrained neural network model for feature extraction and resource classification, and applies it to enhance survey paragraph generation.

Findings

Achieved F1 scores of 0.94 and 0.82 on target domains.

Developed a novel query-document masked language model (QD-MLM).

Released a large corpus of web resources and queries.

Abstract

Effective human learning depends on a wide selection of educational materials that align with the learner's current understanding of the topic. While the Internet has revolutionized human learning or education, a substantial resource accessibility barrier still exists. Namely, the excess of online information can make it challenging to navigate and discover high-quality learning materials. In this paper, we propose the educational resource discovery (ERD) pipeline that automates web resource discovery for novel domains. The pipeline consists of three main steps: data collection, feature extraction, and resource classification. We start with a known source domain and conduct resource discovery on two unseen target domains via transfer learning. We first collect frequent queries from a set of seed documents and search on the web to obtain candidate resources, such as lecture slides and introductory blog posts. Then we introduce a novel pretrained information retrieval deep neural network model, query-document masked language modeling (QD-MLM), to extract deep features of these candidate resources. We apply a tree-based classifier to decide whether the candidate is a positive learning resource. The pipeline achieves F1 scores of 0.94 and 0.82 when evaluated on two similar but novel target domains. Finally, we demonstrate how this pipeline can benefit an application: leading paragraph generation for surveys. This is the first study that considers various web resources for survey generation, to the best of our knowledge. We also release a corpus of 39,728 manually labeled web resources and 659 queries from NLP, Computer Vision (CV), and Statistics (STATS).