Abstract
Topic models are natural language processing models that can parse large collections of documents and automatically discover their main topics. However, conventional topic models fail to capture how such topics change as the collections evolve. To amend this, various researchers have proposed dynamic versions which are able to extract sequences of topics from timestamped document collections. Moreover, a recently-proposed model, the dynamic embedded topic model (DETM), joins such a dynamic analysis with the representational power of word and topic embeddings. In this paper, we propose modifying its word probabilities with a temperature parameter that controls the smoothness/sharpness trade-off of the distributions in an attempt to increase the coherence of the extracted topics. Experimental results over a selection of the COVID-19 Open Research Dataset (CORD-19), the United Nations General Debate Corpus, and the ACL Title and Abstract dataset show that the proposed model – nicknamed DETM-tau after the temperature parameter – has been able to improve the model’s perplexity and topic coherence for all datasets.
Supported by funding from Food Agility CRC Ltd, funded under the Commonwealth Government CRC Program. The CRC Program supports industry-led collaborations between industry, researchers and the community.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Otherwise known as the multinomial distribution. The recent literature on variational inference seems to prefer the “categorical distribution” diction.
References
Alvarez-Melis, D., Saveski, M.: Topic modeling in Twitter: aggregating tweets by conversations. In: The 10th International Conference on Web and Social Media, pp. 519–522 (2016)
Arnold, C., El-Saden, S., Bui, A., Taira, R.: Clinical case-based retrieval using latent topic analysis.In: AMIA Annual Symposium Proceedings, vol. 2010, pp. 26–30 (2010)
Mikhaylov, S.J., Baturo, A., Dasandi, N.: Understanding state preferences with text as data. In: Introducing the UN General Debate Corpus. Research & Politics (2017)
Bengio, Y., Ducharme, R., Vincent, P., Janvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137–1155 (2003)
Bird, S., et al.: The ACL anthology reference corpus: a reference dataset for bibliographic research in computational linguistics. In: International Conference on Language Resources and Evaluation, pp. 1755–1759 (2008)
Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians, pp. 859–877 (2017)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Cecchini, M., Aytug, H., Koehler, G.J., Pathak, P.: Making words work: using financial text as a predictor of financial events. Decis. Support Syst. 50(1), 164–175 (2010)
Devyatkin, D., Nechaeva, E., Suvorov, R., Tikhomirov, I.: Mapping the research landscape of agricultural sciences. Foresight STI Govern. 12(1), 57–76 (2018)
Dieng, A.B., Ruiz, F.J.R., Blei, D.M.: The dynamic embedded topic model (2019)
Dieng, A.B., Ruiz, F.J.R., Blei, D.M.: Topic modeling in embedding spaces. Trans. Assoc. Comput. Linguist. 8, 439–453 (2020)
Kim, H., Drake, B., Endert, A., Park, H.: ArchiText: interactive hierarchical topic modeling. IEEE Trans. Vis. Comput. Graphics 27(9), 3644–3655 (2021)
Lafferty, J.D., Blei, D.M.: The dynamic topic model. In: The 23rd International Conference on Machine Learning, pp. 113–120 (2006)
Lau, J.H., Newman, D., Baldwin, T.: Machine reading tea leaves: automatically evaluating topic coherence and topic model quality. In: The 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), pp. 530–539 (2014)
Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: The 31th International Conference on Machine Learning, vol. 32, pp. 1188–1196 (2014)
Liu, T., Zhang, N.L., Chen, P.: Hierarchical latent tree analysis for topic detection. CoRR, vol. 8725, pp. 256–272 (2014)
Minsky, M.: Steps toward artificial intelligence. Proc. IRE 49(1), 8–30 (1961)
Nguyen, T.H., Shirai, K.: Topic modeling based sentiment analysis on social media for stock market prediction. In: The 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNL 2015), pp. 1354–1364 (2015)
Peng, M., et al.: Neural sparse topical coding. In: The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), pp. 2332–2340 (2018)
Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers, pp. 61–74. MIT Press (1999)
Rodrigues, F., Lourenco, M., Ribeiro, B., Pereira, F.C.: Learning supervised topic models for classification and regression from crowds. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2409–2422 (2017)
Sarioglu, E., Choi, H.-A., Yadav, K.: Clinical report classification using natural language processing and topic modeling. In: The 11th International Conference on Machine Learning and Applications, vol. 2, pp. 204–209 (2012)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. (2018)
Wang, L.L., et al.: CORD-19: the COVID-19 open research dataset. In: 1st Workshop on NLP for COVID-19 at ACL 2020, vol. 1, pp. 1–12 (2020)
Guixian, X., Meng, Y., Chen, Z., Qiu, X., Wang, C., Yao, H.: Research on topic detection and tracking for online news texts. IEEE Access 7, 58407–58418 (2019)
Zhang, A., Zhu, J., Zhang, B.: Sparse online topic models. In: The 22nd International World Wide Web Conference (WWW 2013), pp. 1489–1500 (2013)
Zhang, R., Pakhomov, S., Gladding, S., Aylward, M., Borman-Shoap, E., Melton, G.: Automated assessment of medical training evaluation text. In: AMIA Annual Symposium Proceedings, vol. 2012, pp. 1459–68 (2012)
Zhu, J., Xing, E.P.: Sparse topical coding. In: The 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011), pp. 831–838 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, A., Esmaili, N., Piccardi, M. (2022). A Temperature-Modified Dynamic Embedded Topic Model. In: Park, L.A.F., et al. Data Mining. AusDM 2022. Communications in Computer and Information Science, vol 1741. Springer, Singapore. https://doi.org/10.1007/978-981-19-8746-5_2
Download citation
DOI: https://doi.org/10.1007/978-981-19-8746-5_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8745-8
Online ISBN: 978-981-19-8746-5
eBook Packages: Computer ScienceComputer Science (R0)