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

no code implementations • 7 Jan 2022 • Irene Li, Thomas George, Alexander Fabbri, Tammy Liao, Benjamin Chen, Rina Kawamura, Richard Zhou, Vanessa Yan, Swapnil Hingmire, Dragomir Radev

In this paper, we propose the educational resource discovery (ERD) pipeline that automates web resource discovery for novel domains.

Information Retrieval Language Modelling +4

CLICKER: A Computational LInguistics Classification Scheme for Educational Resources

1 code implementation • 16 Dec 2021 • Swapnil Hingmire, Irene Li, Rena Kawamura, Benjamin Chen, Alexander Fabbri, Xiangru Tang, Yixin Liu, Thomas George, Tammy Liao, Wai Pan Wong, Vanessa Yan, Richard Zhou, Girish K. Palshikar, Dragomir Radev

We propose a classification scheme -- CLICKER for CL/NLP based on the analysis of online lectures from 77 university courses on this subject.

Classification Retrieval

Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains

no code implementations • 17 Sep 2021 • Irene Li, Vanessa Yan, Dragomir Radev

Our novel model consists of a variational graph autoencoder (VGAE) and a domain discriminator.

Link Prediction

Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders

no code implementations • ACL 2021 • Irene Li, Vanessa Yan, Tianxiao Li, Rihao Qu, Dragomir Radev

For example, one may be an expert in the natural language processing (NLP) domain but want to determine the best order to learn new concepts in an unfamiliar Computer Vision domain (CV).