Abstract
Applying conventional autoencoders for textual data often results in learning trivial and redundant representations due to high text dimensionality, sparsity, and following power-law word distribution. To address these challenges, we propose two novel autoencoders, SCAT (Second Chance Autoencoder for Text) and SSCAT (Similarity-based SCAT). Our autoencoders utilize competitive learning among the k winner neurons in the bottleneck layer, which become specialized in recognizing specific patterns, leading to learning more semantically meaningful representations of textual data. In addition, the SSCAT model presents a novel competition based on a similarity measurement to eliminate redundant features. Our experiments prove that SCAT and SSCAT achieve high performance on several tasks, including classification, topic modeling, and document visualization, compared to LDA, k-Sparse, KATE, ProdLDA, NVCTM and ZeroShotTM.The experiments were conducted using the 20 Newsgroups, Wiki10+, and Reuters datasets.
Similar content being viewed by others
Notes
The ProdLDA source code is available at https://github.com/akashgit/autoencoding_vi_for_topic_models.
The ZeroShotTM source code is available at https://github.com/MilaNLProc/contextualized-topic-models
The KATE source code is available at https://github.com/hugochan/KATE
We used the Wilcoxon module in Spacy library: https://spacy.io/.
References
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mané D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: Large-scale machine learning on heterogeneous systems https://www.tensorflow.org/. Software available from tensorflow.org
Bahrani M, Sameti H (2010) A new bigram-plsa language model for speech recognition. EURASIP Journal on Advances in Signal Processing 2010(1):308437
Benavoli A, Corani G, Mangili F, Zaffalon M, Ruggeri F (2014) A bayesian wilcoxon signed-rank test based on the dirichlet process. In: International conference on machine learning. PMLR, pp 1026–1034
Bengio Y (2009) Learning deep architectures for AI. Now Publishers Inc
Bengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. In: Advances in neural information processing systems, pp 153–160
Bianchi F, Terragni S, Hovy D, Nozza D, Fersini E (2020) Cross-lingual contextualized topic models with zero-shot learning. arXiv: 2004.07737
Biju VG, Prashanth C (2017) Friedman and wilcoxon evaluations comparing svm, bagging, boosting, k-nn and decision tree classifiers. Journal of Applied Computer Science Methods 9
Blei DM, Griffiths TL, Jordan MI (2010) The nested chinese restaurant process and bayesian nonparametric inference of topic hierarchies. Journal of the ACM (JACM) 57(2):7
Blei DM, Ng AY, Jordan MI: Latent dirichlet allocation. Journal of machine Learning research 3(Jan), 993–1022 (2003)
Canini K, Shi L, Griffiths T (2009) Online inference of topics with latent dirichlet allocation. In: Artificial Intelligence and Statistics, pp. 65–72
Chen Y, Zaki MJ (2017) Kate: K-competitive autoencoder for text. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, pp 85–94
Chollet, F., et al (2015) Keras. https://github.com/fchollet/keras
Dieng AB, Ruiz FJ, Blei DM (2020) Topic modeling in embedding spaces. Transactions of the Association for Computational Linguistics 8:439–453
Eisenstein J, Ahmed A, Xing EP (2011) Sparse additive generative models of text
Fouladvand S, Mielke MM, Vassilaki M, Sauver JS, Petersen RC, Sohn S (2019) Deep learning prediction of mild cognitive impairment using electronic health records. In: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, pp 799–806
Gharibi G, Walunj V, Alanazi R, Rella S, Lee Y (2019) Automated management of deep learning experiments. In: Proceedings of the 3rd International Workshop on Data Management for End-to-End Machine Learning, pp 1–4
Gharibi G, Walunj V, Rella S, Lee Y (2019) Modelkb: towards automated management of the modeling lifecycle in deep learning. In: 2019 IEEE/ACM 7th International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering (RAISE). IEEE, pp 28–34
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press
Goudarzvand S, Gharibi G, Lee Y (2020) Scat: Second chance autoencoder for textual data. arXiv:2005.06632
Goudarzvand S, Sauver JS, Mielke MM, Takahashi PY, Lee Y, Sohn S (2019) Early temporal characteristics of elderly patient cognitive impairment in electronic health records. BMC medical informatics and decision making 19(4):149
Goudarzvand S, Sauver JS, Mielke MM, Takahashi PY, Sohn S (2018) Analyzing early signals of older adult cognitive impairment in electronic health records. In: 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, pp 1636–1640
Hofmann T (2001) Unsupervised learning by probabilistic latent semantic analysis. Machine learning 42(1–2):177–196
Hosseini M, Maida AS, Hosseini M, Raju G (2020) Inception lstm for next-frame video prediction (student abstract). Proceedings of the AAAI Conference on Artificial Intelligence 34:13809–13810
Jiang H, Rao Y (2005) Axon formation: fate versus growth. Nature neuroscience 8(5):544–546
Kuhn M, Johnson K (2013) Applied predictive modeling in rr
Lang K (1995) Newsweeder: Learning to filter netnews. In: Machine Learning Proceedings 1995. Elsevier, pp 331–339
Larochelle H, Lauly S (2012) A neural autoregressive topic model. In: Advances in Neural Information Processing Systems, pp 2708–2716
Lau JH, Newman D, Baldwin T (2014) Machine reading tea leaves: Automatically evaluating topic coherence and topic model quality. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pp 530–539
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. nature 521(7553):436
Lewis, D.D., Yang, Y., Rose, T.G., Li, F.: Rcv1: A new benchmark collection for text categorization research. Journal of machine learning research 5(Apr), 361–397 (2004)
Liu J, Chang WC, Wu Y, Yang Y (2017) Deep learning for extreme multi-label text classification. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp 115–124
Liu L, Huang H, Gao Y, Zhang Y, Wei X (2019) Neural variational correlated topic modeling. In: The World Wide Web Conference, pp. 1142–1152
Lu X, Tsao Y, Matsuda S, Hori C (2013) Speech enhancement based on deep denoising autoencoder. Interspeech 2013:436–440
Maaloe L, Arngren M, Winther O (2015) Deep belief nets for topic modeling. arXiv:1501.04325
Maaten, L.v.d., Hinton, G.: Visualizing data using t-sne. Journal of machine learning research 9(Nov), 2579–2605 (2008)
Makhzani A, Frey B (2013) K-sparse autoencoders. arXiv:1312.5663
Miao Y, Yu L, Blunsom P (2016) Neural variational inference for text processing. In: International conference on machine learning, pp 1727–1736
Mingorance-Le Meur A (2006) Jnk gives axons a second chance. Journal of Neuroscience 26(47):12104–12105
Nan F, Ding R, Nallapati R, Xiang B (2019) Topic modeling with wasserstein autoencoders. arXiv:1907.12374
O’Mahony N, Campbell S, Carvalho A, Harapanahalli S, Hernandez GV, Krpalkova L, Riordan D, Walsh J (2019) Deep learning vs. traditional computer vision. In: Science and Information Conference. Springer , pp 128–144
Reimers N, Gurevych I (2019) Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv:1908.10084
Rubenstein PK, Schoelkopf B, Tolstikhin I (2018) On the latent space of wasserstein auto-encoders. arXiv:1802.03761
Schneider J, Vlachos M (2018) Topic modeling based on keywords and context. In: Proceedings of the 2018 SIAM International Conference on Data Mining. SIAM, pp 369–377
Srivastava A, Sutton C (2017) Autoencoding variational inference for topic models. arXiv:1703.01488
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15(1):1929–1958
Tolstikhin I, Bousquet O, Gelly S, Schoelkopf B (2017) Wasserstein auto-encoders. arXiv:1711.01558
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research 11(Dec), 3371–3408 (2010)
Wang R, Zhou D, He Y (2019) Atm: Adversarial-neural topic model. Information Processing & Management 56(6):102098
Wang X, Yang Y (2020) Neural topic model with attention for supervised learning. In: International Conference on Artificial Intelligence and Statistics. PMLR, pp 1147–1156
Wang X, Zhao Y, Pourpanah F (2020) Recent advances in deep learning
Wani MA, Bhat FA, Afzal S, Khan AI (2020) Advances in deep learning, vol. 57. Springer
Wei X, Croft WB (2006) Lda-based document models for ad-hoc retrieval. In: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, pp 178–185
Xu Y, Goodacre R (2018) On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. Journal of Analysis and Testing 2(3):249–262
Zhai S, Zhang ZM (2016) Semisupervised autoencoder for sentiment analysis. In: Thirtieth AAAI Conference on Artificial Intelligence
Zhang C, Butepage J, Kjellstrom H, Mandt S (2018) Advances in variational inference. IEEE transactions on pattern analysis and machine intelligence
Zhang Z, Geiger J, Pohjalainen J, Mousa AED, Jin W, Schuller B (2018) Deep learning for environmentally robust speech recognition: An overview of recent developments. ACM Transactions on Intelligent Systems and Technology (TIST) 9(5):1–28
Zhu J, Xing EP (2012) Sparse topical coding. arXiv:1202.3778
Zhu Z, Wang X, Bai S, Yao C, Bai X (2016) Deep learning representation using autoencoder for 3d shape retrieval. Neurocomputing 204:41–50
Zubiaga A (2012) Enhancing navigation on wikipedia with social tags. arXiv:1202.5469
Author information
Authors and Affiliations
Corresponding author
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
Goudarzvand, S., Gharibi, G. & Lee, Y. Similarity-based second chance autoencoders for textual data. Appl Intell 52, 12330–12346 (2022). https://doi.org/10.1007/s10489-021-03100-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-03100-z