Embedding Text in Hyperbolic Spaces

Bhuwan Dhingra, Christopher Shallue, Mohammad Norouzi, Andrew Dai, George Dahl


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 word-context 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.
Anthology ID:
W18-1708
Volume:
Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana, USA
Editors:
Goran Glavaš, Swapna Somasundaran, Martin Riedl, Eduard Hovy
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
59–69
Language:
URL:
https://aclanthology.org/W18-1708
DOI:
10.18653/v1/W18-1708
Bibkey:
Cite (ACL):
Bhuwan Dhingra, Christopher Shallue, Mohammad Norouzi, Andrew Dai, and George Dahl. 2018. Embedding Text in Hyperbolic Spaces. In Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), pages 59–69, New Orleans, Louisiana, USA. Association for Computational Linguistics.
Cite (Informal):
Embedding Text in Hyperbolic Spaces (Dhingra et al., TextGraphs 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-1708.pdf
Data
HyperLexMultiNLIPenn TreebankSNLI