Skip to main content

Probabilistic Approach for Embedding Arbitrary Features of Text

  • Conference paper
  • First Online:
Analysis of Images, Social Networks and Texts (AIST 2018)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 11179))

  • 806 Accesses

Abstract

Topic modeling is usually used to model words in documents by probabilistic mixtures of topics. We generalize this setup and consider arbitrary features of the positions in a corpus, e.g. “contains a word”, “belongs to a sentence”, “has a word in the local context”, “is labeled with a POS-tag”, etc. We build sparse probabilistic embeddings for positions and derive embeddings for the features by averaging of those. Importantly, we interpret the EM-algorithm as an iterative process of intersection and averaging steps that reestimate position and feature embeddings respectively. With this approach, we get several insights. First, we argue that a sentence should not be represented as an average of its words. While each word is a mixture of multiple senses, each word occurrence refers typically to just one specific sense. So in our approach, we obtain sentence embeddings by averaging position embeddings from the E-step. Second, we show that Biterm Topic Model (Yan et al. [11]) and Word Network Topic Model (Zuo et al. [12]) are equivalent with the only difference of tying word and context embeddings. We further extend these models by adjusting representation of each sliding window with a few iterations of EM-algorithm. Finally, we aim at consistent embeddings for hierarchical entities, e.g. for word-sentence-document structure. We discuss two alternative schemes of training and generalize to the case where the middle level of the hierarchy is unknown. It provides a unified formulation for topic segmentation and word sense disambiguation tasks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    bigartm.org

  2. 2.

    github.com/facebookresearch/SentEval

References

  1. Arora, S., Li, Y., Liang, Y., Ma, T., Risteski, A.: Linear algebraic structure of word senses, with applications to polysemy. CoRR abs/1601.03764 (2016)

    Google Scholar 

  2. Arora, S., Liang, Y., Ma, T.: A simple but tough-to-beat baseline for sentence embeddings. In: International Conference on Learning Representations (2017)

    Google Scholar 

  3. Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Bordes, A.: Supervised learning of universal sentence representations from natural language inference data. In: Proceedings of EMNLP, pp. 670–680. Association for Computational Linguistics (2017)

    Google Scholar 

  4. Hofmann, T.: Probabilistic latent semantic analysis. In: Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, UAI 1999, pp. 289–296. Morgan Kaufmann Publishers Inc., San Francisco (1999)

    Google Scholar 

  5. Inan, H., Khosravi, K., Socher, R.: Tying word vectors and word classifiers: A loss framework for language modeling. CoRR abs/1611.01462 (2016)

    Google Scholar 

  6. Kiros, R., et al.: Skip-thought vectors. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, NIPS 2015, pp. 3294–3302. MIT Press, Cambridge (2015)

    Google Scholar 

  7. Kochedykov, D., Apishev, M., Golitsyn, L., Vorontsov, K.: Fast and modular regularized topic modelling. In: Proceeding of the 21st Conference of FRUCT Association, ISMW, pp. 182–193 (2017)

    Google Scholar 

  8. Pagliardini, M., Gupta, P., Jaggi, M.: Unsupervised learning of sentence embeddings using compositional n-gram features. In: Proceedings of NAACL (2018)

    Google Scholar 

  9. Potapenko, A., Popov, A., Vorontsov, K.: Interpretable probabilistic embeddings: bridging the gap between topic models and neural networks. In: Filchenkov, A., Pivovarova, L., Žižka, J. (eds.) AINL 2017. CCIS, vol. 789, pp. 167–180. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-71746-3_15

    Chapter  Google Scholar 

  10. Press, O., Wolf, L.: Using the output embedding to improve language models. In: Proceedings of ACL: Volume 2, Short Papers, pp. 157–163. ACL (2017)

    Google Scholar 

  11. Yan, X., Guo, J., Lan, Y., Cheng, X.: A biterm topic model for short texts. In: Proceedings of WWW, pp. 1445–1456 (2013)

    Google Scholar 

  12. Zuo, Y., Zhao, J., Xu, K.: Word network topic model: a simple but general solution for short and imbalanced texts. Knowl. Inf. Syst. 48(2), 379–398 (2016)

    Article  Google Scholar 

Download references

Acknowledgements

The research was supported by Russian Foundation for Basic Research (17-07-01536).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Anna Potapenko .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Potapenko, A. (2018). Probabilistic Approach for Embedding Arbitrary Features of Text. In: van der Aalst, W., et al. Analysis of Images, Social Networks and Texts. AIST 2018. Lecture Notes in Computer Science(), vol 11179. Springer, Cham. https://doi.org/10.1007/978-3-030-11027-7_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-11027-7_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-11026-0

  • Online ISBN: 978-3-030-11027-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics