Abstract
We present an effective word and document matrix representation architecture based on a linear operation, referred to as doc2matrix, to learn representations for document-level classification. It uses a matrix to present each word or document, which is different from the traditional form of vector representation. Doc2matrix defines proper subwindows as the scale of text. A word matrix and a document matrix are generated by stacking the information of these subwindows. Our document matrix not only contains more fine-grained semantic and syntactic information than the original representation but also introduces abundant two-dimensional features. Experiments conducted on four document-level classification tasks demonstrate that the proposed architecture can generate higher-quality word and document representations and outperform previous models based on linear operations. We can see that compared to different classifiers, a convolutional-based classifier is more suitable for our document matrix. Furthermore, we also demonstrate that the convolution operation can better capture the two-dimensional features of the proposed document matrix by the analysis from both theoretical and experimental perspectives.
Similar content being viewed by others
References
Harris ZS (1981) Distributional structure. Word 10:146–162
Silva J, Coheur L, Mendes AC, Wichert A (2011) From symbolic to sub-symbolic information in question classification. Artif Intell Rev 35(2):137–154
Mikolov T et al (2013) Efficient estimation of word representations in vector space. In: Computer science
Zhang H, Wang S, Xu X et al (2018) Tree2Vector: learning a vectorial representation for tree-structured data. IEEE Trans Neural Netw Learn Syst 99:1–15
Zhang H, Wang S, Zhao M et al (2018) Locality reconstruction models for book representation. IEEE Trans Knowl Data Eng 30:1873–1886
Le QV, Mikolov T (2014) Distributed representations of sentences and documents. In: Computer science
Chen M (2017) Efficient vector representation for documents through corruption. In: Proceedings of the fifth international conference on learning representations. ICLR
Socher R, Perelygin A, Wu JY, Chuang J, Manning CD, Ng AY, Potts C (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of conference on empirical methods in natural language processing. EMNLP, pp 1642
Mesnil et al (2015) Ensemble of generative and discriminative techniques for sentiment analysis of movie reviews. J Lightwave Technol 32(17):3043–3060
Zhang H et al (2013) Multidimensional latent semantic analysis using term spatial information. IEEE Trans Cybern 43:1625–1640
Huang EH, Socher R, Manning CD et al (2012) Improving word representations via global context and multiple word prototypes. In: Proceedings of meeting of the Association for Computational Linguistics: long papers
Kim Y (2014). Convolutional neural networks for sentence classification. In: Proceedings of conference on empirical methods in natural language processing. EMNLP, pp 1746–1751
Kim Y, Jernite Y, Sontag D et al (2016) Character-aware neural language models. In: Proceedings of the thirtieth AAAI conference on artificial intelligence. AAAI, pp 2741–2749
Conneau A, Schwenk H et al (2016) Very deep convolutional networks for text classification. In: Proceedings of the 15th conference of the European chapter of the Association for Computational Linguistics, vol 1, long papers
Shen D, Min MR, Li Y et al (2017) Learning context-sensitive convolutional filters for text processing
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computation 9(8):1735–1780
Zhou C, Sun C, Liu Z, et al (2015) A C-LSTM neural network for text classification. In: Computer science, pp 39–44
Ding Z, Xia R, Yu J, et al (2018) Densely connected bidirectional LSTM with applications to sentence classification. In: Natural language processing and chinese computing, pp 278–287
Pappas N, Popescu-Belis A (2017) Multilingual hierarchical attention networks for document classification
Kumar A, Kawahara D, Kurohashi S (2018) Knowledge-enriched two-layered attention network for sentiment analysis
Zhang T, Huang M, Zhao L (2018) Learning structured representation for text classification via reinforcement learning. In: Proceedings of the thirty-second AAAI conference on artificial intelligence. AAAI
Feng J, Huang M, Zhao L et al (2018) Reinforcement learning for relation classification from noisy data. In: Proceedings of the thirty-second AAAI conference on artificial intelligence. AAAI
Miyato T, Dai A M, Goodfellow I (2017) Adversarial training methods for semi-supervised text classification. In: Proceedings of the fifth international conference on learning representations. ICLR
Liu P, Qiu X, Huang X (2017) Adversarial multi-task learning for text classification
Maas AL, Daly RE, Pham PT, Huang D, Ng AY, Potts C (2011) Learning word vectors for sentiment analysis. Meeting of the Association for Computational Linguistics. ACL, pp 142–150
Johnson R, Zhang T (2015) Semi-supervised convolutional neural networks for text categorization via region embedding. In: Advances in neural information processing systems, pp 919–927
Joachims T (1996) A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization. In: ICML, pp 143–151
Vincent P, Larochelle H, Bengio Y, Manzagol P-A (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the twenty-fifth international conference. ICML, pp 1096–1103
Mikolov T et al (2010) Recurrent neural network based language model. In: Proceedings of the 37th international symposium on computer architecture. ISCA, pp 1045–1048
Fan RE, Chang KW, Hsieh CJ et al (2008) LIBLINEAR: a library for large linear classification. J Mach Learn Res 9:1871–1874
Acknowledgements
This work was supported by the Innovation Foundation of Science and Technology of Dalian under grant No.2018J12GX045.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Human and animal rights
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Guo, S., Yao, N. Generating word and document matrix representations for document classification. Neural Comput & Applic 32, 10087–10108 (2020). https://doi.org/10.1007/s00521-019-04541-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-019-04541-x