Abstract
A high degree of topical diversity is often considered to be an important characteristic of interesting text documents. A recent proposal for measuring topical diversity identifies three elements for assessing diversity: words, topics, and documents as collections of words. Topic models play a central role in this approach. Using standard topic models for measuring diversity of documents is suboptimal due to generality and impurity. General topics only include common information from a background corpus and are assigned to most of the documents in the collection. Impure topics contain words that are not related to the topic; impurity lowers the interpretability of topic models and impure topics are likely to get assigned to documents erroneously. We propose a hierarchical re-estimation approach for topic models to combat generality and impurity; the proposed approach operates at three levels: words, topics, and documents. Our re-estimation approach for measuring documents’ topical diversity outperforms the state of the art on PubMed dataset which is commonly used for diversity experiments.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
As the DR level of re-estimation directly employs the parsimonious language modeling techniques in [9], we omit it from our in-depth analysis.
- 2.
We use a dump of June 2, 2015, containing 15.6 million articles.
- 3.
Available at http://www.ai.mit.edu/people/~jrennie/20Newsgroups/.
- 4.
Available at http://disi.unitn.it/moschitti/corpora.htm.
References
U.S. National Library of Medicine. Pubmed Central Open Access Initiative (2010)
Azarbonyad, H., Saan, F., Dehghani, M., Marx, M., Kamps, J.: Are topically diverse documents also interesting? In: Mothe, J., Savoy, J., Kamps, J., Pinel-Sauvagnat, K., Jones, G.J.F., SanJuan, E., Cappellato, L., Ferro, N. (eds.) CLEF 2015. LNCS, vol. 9283, pp. 215–221. Springer, Cham (2015). doi:10.1007/978-3-319-24027-5_19
Bache, K., Newman, D., Smyth, P.: Text-based measures of document diversity. In KDD (2013)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(4–5), 993–1022 (2003)
Boyd-Gaber, J., Mimno, D., Newman, D.: Care and feeding of topic models. In: Mixed Membership Models & Their Applic. CRC Press (2014)
Dehghani, M., Azarbonyad, H., Kamps, J., Marx, M.: Two-way parsimonious classification models for evolving hierarchies. In: Fuhr, N., Quaresma, P., Gonçalves, T., Larsen, B., Balog, K., Macdonald, C., Cappellato, L., Ferro, N. (eds.) CLEF 2016. LNCS, vol. 9822, pp. 69–82. Springer, Heidelberg (2016). doi:10.1007/978-3-319-44564-9_6
Dehghani, M., Azarbonyad, H., Kamps, J., Marx, M.: On horizontal and vertical separation in hierarchical text classification. In: ICTIR (2016)
Derzinski, M., Rohanimanesh, K.: An information theoretic approach to quantifying text interestingness. In: NIPS MLNLP Workshop (2014)
Hiemstra, D., Robertson, S., Zaragoza, H.: Parsimonious language models for information retrieval. In: SIGIR (2004)
Lacoste-Julien, S., Sha, F., Jordan, M.I.: DiscLDA: discriminative learning for dimensionality reduction and classification. In: NIPS (2009)
Lau, J.H., Newman, D., Baldwin, T.: Machine reading tea leaves: automatically evaluating topic coherence and topic model quality. In: EACL (2014)
Lewis, D.D., Yang, Y., Rose, T.G., Li, F.: RCV1: a new benchmark collection for text categorization research. J. Mach. Learn. Res. 5, 361–397 (2004)
Lin, T., Tian, W., Mei, Q., Cheng, H.: The dual-sparse topic model: Mining focused topics and focused terms in short text. In: WWW (2014)
Manning, C.D., Raghavan, P., SchĂĽtze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)
Mehrotra, R., Sanner, S., Buntine, W., Xie, L.: Improving LDA topic models for microblogs via tweet pooling and automatic labeling. In: SIGIR (2013)
Nguyen, D.Q., Billingsley, R., Du, L., Johnson, M.: Improving topic models with latent feature word representations. Trans. Assoc. Comput. Linguist. 3, 299–313 (2015)
Rao, C.: Diversity and dissimilarity coefficients: a unified approach. Theoret. Popul. Biol. 21(1), 24–43 (1982)
Röder, M., Both, A., Hinneburg, A.: Exploring the space of topic coherence measures. In: WSDM (2015)
Soleimani, H., Miller, D.: Parsimonious topic models with salient word discovery. IEEE Trans. Knowl. Data Eng. 27(3), 824–837 (2015)
Solow, A., Polasky, S., Broadus, J.: On the measurement of biological diversity. J. Environ. Econ. Manag. 24(1), 60–68 (1993)
Wallach, H.M., Mimno, D.M., McCallum, A.: Rethinking LDA: why priors matter. In: NIPS (2009)
Wang, C., Blei, D.M.: Decoupling sparsity and smoothness in the discrete hierarchical dirichlet process. In: NIPS (2009)
Williamson, S., Wang, C., Heller, K.A., Blei, D.M.: The IBP compound Dirichlet process and its application to focused topic modeling. In: ICML (2010)
Xie, P., Xing, E.P.: Integrating document clustering and topic modeling. In: UAI (2013)
Yan, X., Guo, J., Lan, Y., Cheng, X.: A biterm topic model for short texts. In: WWW (2013)
Zhai, C., Lafferty, J.: Model-based feedback in the language modeling approach to information retrieval. In: CIKM (2001)
Acknowledgments
This research was supported by Ahold Delhaize, Amsterdam Data Science, Blendle, the Bloomberg Research Grant program, the Dutch national program COMMIT, Elsevier, the European Community’s Seventh Framework Programme (FP7/2007-2013) under grant agreements nr 283465 (ENVRI) and 312827 (VOX-Pol), the Microsoft Research Ph.D. program, the Netherlands eScience Center under project number 027.012.105, the Netherlands Institute for Sound and Vision, the Netherlands Organisation for Scientific Research (NWO) under project nrs 314.99.108, 600.006.014, HOR-11-10, CI-14-25, 652.-002.-001, 612.-001.-551, 652.-001.-003, 314-98-071, and Yandex. All content represents the opinion of the authors, which is not necessarily shared or endorsed by their respective employers and/or sponsors.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Azarbonyad, H., Dehghani, M., Kenter, T., Marx, M., Kamps, J., de Rijke, M. (2017). Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity. In: Jose, J., et al. Advances in Information Retrieval. ECIR 2017. Lecture Notes in Computer Science(), vol 10193. Springer, Cham. https://doi.org/10.1007/978-3-319-56608-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-56608-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-56607-8
Online ISBN: 978-3-319-56608-5
eBook Packages: Computer ScienceComputer Science (R0)