Abstract
Document classification plays an important role in natural language processing. Among that, keyword extraction algorithm shows its great potential in summarizing the entire document. Attention is the process of selectively concentrating on a discrete aspect of information, while ignoring other perceivable information. A new probabilistic keyword extraction algorithm is proposed, which is inspired by the visual attention mechanism. An unsupervised neural network based pre-training method is proposed for training the semantic attention based keyword extraction algorithm, which is helpful in extracting keywords with rich contextual information from the document. A bidirectional Long short-term memory network combined with the proposed semantic keyword extraction algorithm is designed for both topic and sentiment classification tasks. Experiments on four large scale datasets show that the proposed visual attention based keyword extraction algorithm gives a better performance than the baseline methods. The semantic attention based keyword extraction method is significant in summarizing the content of a document, which is very useful for large scale document classification.
Similar content being viewed by others
References
Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate, arXiv:1409.0473
Cheng J, Lapata M (2016) Neural summarization by extracting sentences and words, arXiv:1603.07252
Chung J, Gulcehre C et al (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv:1412.3555
Graves A, Jaitly N (2014) Towards end-to-end speech recognition with recurrent neural networks. In: Proceedings of the 31st international conference on machine learning, pp 1764–1772
Guo Z, Gao L, Song J et al (2016) Attention-based LSTM with semantic consistency for videos captioning. In: Proceedings of the 2016 ACM on multimedia conference. ACM, pp 357–361
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Jianfei N, Jiangzhen L (2016) Using Word2vec with TextRank to extract keywords. New Technology of Library and Information Service, pp 20–27
Kim Y (2014) Convolutional neural networks for sentence classification, arXiv:1408.5882
Krizhevsky A, Sutskever I, Hinton G E (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst 1097–1105
LeCun Y, Bottou L, Bengio Y et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521 (7553):436–444
Li J, Sun M (2007) Scalable term selection for text categorization. In: EMNLP-CoNLL, pp 774–782
Matsuo Y, Ishizuka M (2004) Keyword extraction from a single document using word co-occurrence statistical information. Int J Artif Intell Tools 13(01):157–169
Mikolov T, Sutskever I, Chen K et al (2013) Distributed representations of words and phrases and their compositionality. Adv Neural Inf Proces Syst 3111–3119
Mnih V, Heess N, Graves A (2014) Recurrent models of visual attention. Adv Neural Inf Proces Syst 256–264
Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543
Song J, Guo Z, Gao L et al (2017) Hierarchical LSTM with adjusted temporal attention for video captioning. In: IJCAI
Tang D, Qin B, Liu T (2015) Document modeling with gated recurrent neural network for sentiment classification. In: EMNLP, pp 1422–1432
Xu K, Ba J, Kiros R et al (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning, pp 2048–2057
Yelp Dataset Challenge 2017, https://www.yelp.com/dataset/challenge (2017)
Yuepeng L, Cui J, Junchuan J (2015) A keyword extraction algorithm based on Word2vec. E-science Technol Appl 4(2015):54–59
Zhang Y, Lai G, Zhang M et al (2014) Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In: Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval. ACM, pp 83–92
Zhang X, Zhao J, LeCun Y (2015) Character-level convolutional networks for text classification. Adv Neural Inf Proces Syst 649–657
Acknowledgements
This paper is supported by the project 61303094 supported by National Natural Science Foundation of China, by the Science and Technology Commission of Shanghai Municipality 16511102400 and 16111107800, by Innovation Program of Shanghai Municipal Education Commission (14YZ024).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wu, X., Du, Z. & Guo, Y. A visual attention-based keyword extraction for document classification. Multimed Tools Appl 77, 25355–25367 (2018). https://doi.org/10.1007/s11042-018-5788-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-5788-9