| 279 | 4 | 163 |
| 下载次数 | 被引频次 | 阅读次数 |
如今，MOOC学习平台上可用的视频资源呈指数级增长，帮助学习者推荐视频学习顺序成为研究热点。MOOC视频依赖关系可以用于MOOC视频排序和先验知识回顾。首先，提出了一种基于词向量和深度学习模型相结合的MOOC视频依赖识别模型；然后，使用该模型预测MOOC视频依赖关系。实验结果表明，BERT-LSTM模型可以从字幕中有效提取更多的隐含语义特征，完成MOOC视频依赖关系识别。在4个领域中，BERT-LSTM的平均F1值比其他模型高至少6.19%。此外，通过特征提取自动识别MOOC依赖关系方法也具有良好的推广性。
Abstract：The video resources on the learning platform MOOC have grown exponentially. It was a research hotspot to found the order in which learners should follow during their studying the videos. MOOC video prerequisite relations were used for MOOC video sorting and reassessing prior knowledge.Firstly, a MOOC video prerequisite relations recognition model was proposed based on a combination of word vectors and deep learning models. Then these models were used to predict MOOC video prerequisite relations. The experiments showed that the BERT-LSTM model could effectively extract more implicit semantic features from subtitles to detect MOOC videos prerequisite relations. In four fields, The F1 value of BERT-LSTM model was higher than that in other models by more than 6.19%. Additionally, automatic identifying MOOC prerequisite relations through feature extraction also had good generalization.
[1] AL-MUHAIDEB S,MENAI M E B.Evolutionary computation approaches to the curriculum sequencing problem[J].Natural computing,2011,10(2):891-920.
[2] KARAMPIPERIS P,SAMPSON D.Adaptive learning resources sequencing in educational hypermedia systems[J].Journal of educational technology and society,2005,8(4):128-147.
[3] LIMONGELLI C,SCIARRONE F,TEMPERINI M,et al.Adaptive learning with the LS-plan system:a field evaluation[J].IEEE transactions on learning technologies,2009,2(3):203-215.
[4] MIHALCEA R,TARAU P.Textrank:bringing order into text[C]//Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing.Massachusetts:MIT Press,2004:404-411.
[5] TIXIER A,MALLIAROS F,VAZIRGIANNIS M.A graph degeneracy-based approach to keyword extraction[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.Austin:ACL Press,2016:1860-1870.
[6] TALUKDAR P,COHEN W.Crowdsourced comprehension:predicting prerequisite structure in wikipedia[C]//Proceedings of the Seventh Workshop on Building Educational Applications Using NLP.Massachusetts:MIT Press,2012:307-315.
[7] LIANG C,WU Z H,HUANG W Y,et al.Measuring prerequisite relations among concepts[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Lisbon:ACL Press,2015:1668-1674.
[8] LIANG C,YE J,WU Z,et al.Recovering concept prerequisite relations from university course dependencies[C]//Thirty-First AAAI Conference on Artificial Intelligence.Palo Alto:AAAI Press,2017:4786-4791.
[9] SAYYADIHARIKANDEH M,GORDON J,AMBITE J L,et al.Finding prerequisite relations using the wikipedia clickstream[C]//Companion Proceedings of the 2019 World Wide Web Conference.New York:ACM Press,2019:1240-1247.
[10] 邵恒，冯兴乐，包芬.基于深度学习的文本相似度计算[J].郑州大学学报(理学版),2020,52(1):66-71,78.SHAO H,FENG X L,BAO F.Text similarity computation based on deep-learning[J].Journal of Zhengzhou university (natural science edition),2020,52(1):66-71,78.
[11] 陈潇，李逸薇，刘欢，等.基于网络表示的半监督问答文本情感分类方法[J].郑州大学学报(理学版),2020,52(2):52-58.CHEN X,LEE S,LIU H,et al.A semi-supervised sentiment classification method towards question-answering text based on network representation[J].Journal of Zhengzhou university (natural science edition),2020,52(2):52-58.
[12] CHAPLOT D S,YANG Y,CARBONELL J,et al.Data-driven automated induction of prerequisite structure graphs[J].International educational data mining society,2016:318-323.
[13] PAN L M,LI C J,LI J Z,et al.Prerequisite relation learning for concepts in MOOCs[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:ACL Press,2017:1447-1456.
[14] SHEN S S,LEE H Y,LI S W,et al.Structuring lectures in massive open online courses (MOOCs) for efficient learning by linking similar sections and predicting prerequisites[C]//Sixteenth Annual Conference of the International Speech Communication Association.London:Academic Press,2015:1363-1367.
[15] MANRIQUE R,PEREIRA B,MARINO O,et al.Towards the identification of concept prerequisites via knowledge graphs[C]//2019 IEEE 19th International Conference on Advanced Learning Technologies (ICALT).Piscataway:IEEE Press,2019:332-336.
[16] MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space[EB/OL].(2013-07-16)[2021-04-20].https://arxiv.org/abs/1301.3781v1.
[17] BOJANOWSKI P,GRAVE E,JOULIN A,et al.Enriching word vectors with subword information[J].Transactions of the association for computational linguistics,2017,5:135-146.
[18] DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[EB/OL].(2018-11-11)[2021-04-21].https://arxiv.org/abs/1810.04805.
[19] CHO K,VAN MERRIENBOER B,GULCEHRE C,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[EB/OL].(2014-12-11)[2021-04-21].https://aclanthology.org/D14-1179/.
[20] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural computation,1997,9(8):1735-1780.
[21] CHUNG J,GULCEHRE C,CHO K,et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL].(2014-12-11)[2021-04-21].https://www.researchgate.net/publication/269416998_Empirical_Evaluation_of_Gated_Recurrent_Neural_Networks_on_Sequence_Modeling.
[22] YAMADA I,ASAI A,SAKUMA J,et al.Wikipedia2Vec:an efficient toolkit for learning and visualizing the embeddings of words and entities from wikipedia[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing:System Demonstrations.Stroudsburg:ACL Press,2020:23-30.
基本信息:
DOI：10.13705/j.issn.1671-6841.2021304
中图分类号:TP18;TP391.3
引用信息:
[1]白友恒,肖奎,张,等.基于深度学习模型的MOOC视频依赖关系识别方法[J],2022,54(05):29-36.DOI:10.13705/j.issn.1671-6841.2021304.
基金信息:
国家自然科学基金项目(61977021);; 湖北省科技厅重大专项项目(2018ACA133,2019ACA144);; 湖北省教育厅科研计划项目(D20191002)