Embedding Words in Non-Vector Space with Unsupervised Graph Learning

Max Ryabinin, Sergei Popov, Liudmila Prokhorenkova, Elena Voita


Abstract
It has become a de-facto standard to represent words as elements of a vector space (word2vec, GloVe). While this approach is convenient, it is unnatural for language: words form a graph with a latent hierarchical structure, and this structure has to be revealed and encoded by word embeddings. We introduce GraphGlove: unsupervised graph word representations which are learned end-to-end. In our setting, each word is a node in a weighted graph and the distance between words is the shortest path distance between the corresponding nodes. We adopt a recent method learning a representation of data in the form of a differentiable weighted graph and use it to modify the GloVe training algorithm. We show that our graph-based representations substantially outperform vector-based methods on word similarity and analogy tasks. Our analysis reveals that the structure of the learned graphs is hierarchical and similar to that of WordNet, the geometry is highly non-trivial and contains subgraphs with different local topology.
Anthology ID:
2020.emnlp-main.594
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7317–7331
Language:
URL:
https://aclanthology.org/2020.emnlp-main.594
DOI:
10.18653/v1/2020.emnlp-main.594
Bibkey:
Cite (ACL):
Max Ryabinin, Sergei Popov, Liudmila Prokhorenkova, and Elena Voita. 2020. Embedding Words in Non-Vector Space with Unsupervised Graph Learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7317–7331, Online. Association for Computational Linguistics.
Cite (Informal):
Embedding Words in Non-Vector Space with Unsupervised Graph Learning (Ryabinin et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.594.pdf
Video:
 https://slideslive.com/38938816
Code
 yandex-research/graph-glove