Abstract
Topics generated by topic models are usually represented by lists of t terms or alternatively using short phrases or images. The current state-of-the-art work on labeling topics using images selects images by re-ranking a small set of candidates for a given topic. In this paper, we present a more generic method that can estimate the degree of association between any arbitrary pair of an unseen topic and image using a deep neural network. Our method achieves better runtime performance O(n) compared to \(O(n^2)\) for the current state-of-the-art method, and is also significantly more accurate.
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
References
Aletras, N., Baldwin, T., Lau, J.H., Stevenson, M.: Representing topics labels for exploring digital libraries. In: JCDL (2014)
Aletras, N., Baldwin, T., Lau, J.H., Stevenson, M.: Evaluating topic representations for exploring document collections. JASIST (2015)
Aletras, N., Stevenson, M.: Representing topics using images. In: NAACL-HLT, pp. 158–167 (2013)
Aletras, N., Stevenson, M.: Labelling topics using unsupervised graph-based methods. In: ACL (2014)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. JMLR 3, 993–1022 (2003)
Chaney, A.J.B., Blei, D.M.: Visualizing topic models. In: ICWSM, pp. 419–422 (2012)
Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: ICML, pp. 160–167 (2008)
Croft, B.W., Metzler, D., Strohman, T.: Search Engines: Information Retrieval in Practice. Addison-Wesley, Boston (2009)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)
Järvelin, K., Kekäläinen, J.: Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. 20(4), 422–446 (2002)
Lau, J.H., Grieser, K., Newman, D., Baldwin, T.: Automatic labelling of topic models. In: ACL-HLT, pp. 1536–1545 (2011)
Levy, O., Goldberg, Y.: Dependency-based word embeddings. In: ACL, pp. 302–308 (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Smith, A., Hawes, T., Myers, M.: Hierarchy: visualization for hierarchical topic models. In: Workshop on Interactive Language Learning, Visualization, and Interfaces, pp. 71–78 (2014)
Snyder, J., Knowles, R., Dredze, M., Gormley, M., Wolfe, T.: Topic models and metadata for visualizing text corpora. In: NAACL-HLT, pp. 5–9 (2013)
Socher, R., Lin, C.C., Manning, C., Ng, A.Y.: Parsing natural scenes and natural language with recursive neural networks. In: ICML, pp. 129–136 (2011)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15(1), 1929–1958 (2014)
Tieleman, T., Hinton, G.: Lecture 6.5-RMSProp. COURSERA: Neural networks for machine learning (2012)
Wan, X., Wang, T.: Automatic labeling of topic models using text summaries. In: ACL, pp. 2297–2305 (2016)
Weston, J., Bengio, S., Usunier, N.: Large scale image annotation: learning to rank with joint word-image embeddings. Mach. Learn. 81(1), 21–35 (2010)
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
Aletras, N., Mittal, A. (2017). Labeling Topics with Images Using a Neural Network. 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_40
Download citation
DOI: https://doi.org/10.1007/978-3-319-56608-5_40
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)