Embedding Text in Hyperbolic Spaces
Bhuwan
Dhingra
author
Christopher
Shallue
author
Mohammad
Norouzi
author
Andrew
Dai
author
George
Dahl
author
2018-06
text
Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)
Goran
Glavaš
editor
Swapna
Somasundaran
editor
Martin
Riedl
editor
Eduard
Hovy
editor
Association for Computational Linguistics
New Orleans, Louisiana, USA
conference publication
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.
dhingra-etal-2018-embedding
10.18653/v1/W18-1708
https://aclanthology.org/W18-1708
2018-06
59
69