Publications -> Conference Papers

A Novel Cascade Model for Learning Latent Similarity from Heterogeneous Sequential Data of MOOC


Authors: Z. Jiang, S. Feng, G. Cong, C. Miao, and X. Li
Title: A Novel Cascade Model for Learning Latent Similarity from Heterogeneous Sequential Data of MOOC
Abstract: Recent years have witnessed the proliferation of Massive Open Online Courses (MOOCs). With massive learners being offered MOOCs, there is a demand that the forum contents within MOOCs need to be classified in order to facilitate both learners and instructors. Therefore we investigate a significant application, which is to associate forum threads to subtitles of video clips. This task can be regarded as a document ranking problem, and the key is how to learn a distinguishable text representation from word sequences and learners’ behavior sequences. In this paper, we propose a novel cascade model, which can capture both the latent semantics and latent similarity by modeling MOOC data. Experimental results on two real-world datasets demonstrate that our textual representation outperforms state-of-the-art unsupervised counterparts for the application.
Keywords: 
Conference Name: 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP'17)
Location: Copenhagen, Denmark
Publisher: Association for Computational Linguistics
Year: 2017
Accepted PDF File: A_Novel_Cascade_Model_for_Learning_Latent_Similarity_from_Heterogeneous_Sequential_Data_of_MOOC_accepted.pdf
Permanent Link: http://www.aclweb.org/anthology/D17-1292
Reference: Z. Jiang, S. Feng, G. Cong, C. Miao, and X. Li, “A novel cascade model for learning latent similarity from heterogeneous sequential data of MOOC,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP’17). Association for Computational Linguistics, September 2017, pp. 2758–2763.
bibtex: 
@inproceedings{LILY-c133, 
    author = {Jiang, Zhuoxuan  and  Feng, Shanshan  and  Cong, Gao  and  Miao, Chunyan  and  Li, Xiaoming},
    title  = {A Novel Cascade Model for Learning Latent Similarity from Heterogeneous Sequential Data of {MOOC}},  
    booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP'17)}, 
    year  = {2017}, 
    month = {September}, 
    pages = {2758-2763}, 
    location = {Copenhagen, Denmark},
    publisher = {Association for Computational Linguistics},
 }