Paper · 2018 · Open access

Embedding Text in Hyperbolic Spaces

Bhuwan Dhingra, Christopher J. Shallue, Mohammad Norouzi, Andrew M. Dai, George E. Dahl

Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), 59–69 · Published 1 January 2018 · DOI 10.18653/v1/w18-1708

Open PDFView at the publisherCite this paper

In brief

“Embedding Text in Hyperbolic Spaces” is a 2018 paper by Bhuwan Dhingra and 4 co-authors, published in Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12). OpenAlex counts 211 citations as of 19 November 2026, which puts it in the top 7% of works published in 2018 by citations. It is open access under a CC BY licence: the full text is free to read.

Citations
211
Most cited in
2021 (37)
Field-weighted impact
6.57
References
41
Authors
5

Abstract

Natural language text exhibits hierarchical structure in a variety of respects.Ideally, we could incorporate our prior knowledge of this hierarchical structure into unsupervised learning algorithms that work on text data.Recent work by Nickel and Kiela (2017) proposed using hyperbolic instead of Euclidean embedding spaces to represent hierarchical data and demonstrated encouraging results when embedding graphs.In this work, we extend their method with a re-parameterization technique that allows us to learn hyperbolic embeddings of arbitrarily parameterized objects.We apply this framework to learn word and sentence embeddings in hyperbolic space in an unsupervised manner from text corpora.The resulting embeddings seem to encode certain intuitive notions of hierarchy, such as wordcontext frequency and phrase constituency.However, the implicit continuous hierarchy in the learned hyperbolic space makes interrogating the model's learned hierarchies more difficult than for models that learn explicit edges between items.The learned hyperbolic embeddings show improvements over Euclidean embeddings in some -but not all -downstream tasks, suggesting that hierarchical organization is more useful for some tasks than others.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Dhingra, B., Shallue, C. J., Norouzi, M., Dai, A. M., & Dahl, G. E. (2018). Embedding Text in Hyperbolic Spaces. Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), 59–69. https://doi.org/10.18653/v1/w18-1708

MLA 9

Dhingra, Bhuwan, et al. “Embedding Text in Hyperbolic Spaces.” Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), 2018, pp. 59–69. https://doi.org/10.18653/v1/w18-1708.

Chicago

Dhingra, Bhuwan, Christopher J. Shallue, Mohammad Norouzi, Andrew M. Dai, and George E. Dahl. 2018. “Embedding Text in Hyperbolic Spaces.” Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12): 59–69. https://doi.org/10.18653/v1/w18-1708.

Harvard

Dhingra, B. et al. (2018) ‘Embedding Text in Hyperbolic Spaces’, Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), pp. 59–69. doi:10.18653/v1/w18-1708.

IEEE

B. Dhingra, C. J. Shallue, M. Norouzi, A. M. Dai, and G. E. Dahl, “Embedding Text in Hyperbolic Spaces,” Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), pp. 59–69, 2018, doi: 10.18653/v1/w18-1708.

BibTeX

@article{dhingra2018embedding,
  title     = {{Embedding Text in Hyperbolic Spaces}},
  author    = {Dhingra, Bhuwan and Shallue, Christopher J. and Norouzi, Mohammad and Dai, Andrew M. and Dahl, George E.},
  journal   = {Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)},
  year      = {2018},
  pages     = {59--69},
  doi       = {10.18653/v1/w18-1708},
  url       = {https://doi.org/10.18653/v1/w18-1708}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201844
20192323
20201919
20213737
20221818
20232525
20242828
20253232
20262525

Its field-weighted citation impact is 6.57: it has been cited 6.57 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling

  • hyperbolic embeddings
  • word embeddings
  • sentence embeddings
  • unsupervised learning
  • reparameterization
  • hyperbolic space
  • hierarchy

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Dhingra, B., Shallue, C. J., Norouzi, M., Dai, A. M., & Dahl, G. E. (2018). Embedding Text in Hyperbolic Spaces. Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), 59–69. https://doi.org/10.18653/v1/w18-1708

How many times has this paper been cited?

211 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: sign in and open the PDF from this page.

Who wrote this paper?

Bhuwan Dhingra, Christopher J. Shallue, Mohammad Norouzi, Andrew M. Dai, George E. Dahl.

What is the DOI of this paper?

10.18653/v1/w18-1708, permanently at https://doi.org/10.18653/v1/w18-1708. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.