Word Embeddings as Metric Recovery in Semantic Spaces

Tatsunori B. Hashimoto, David Alvarez-Melis, Tommi S. Jaakkola


Abstract
Continuous word representations have been remarkably useful across NLP tasks but remain poorly understood. We ground word embeddings in semantic spaces studied in the cognitive-psychometric literature, taking these spaces as the primary objects to recover. To this end, we relate log co-occurrences of words in large corpora to semantic similarity assessments and show that co-occurrences are indeed consistent with an Euclidean semantic space hypothesis. Framing word embedding as metric recovery of a semantic space unifies existing word embedding algorithms, ties them to manifold learning, and demonstrates that existing algorithms are consistent metric recovery methods given co-occurrence counts from random walks. Furthermore, we propose a simple, principled, direct metric recovery algorithm that performs on par with the state-of-the-art word embedding and manifold learning methods. Finally, we complement recent focus on analogies by constructing two new inductive reasoning datasets—series completion and classification—and demonstrate that word embeddings can be used to solve them as well.
Anthology ID:
Q16-1020
Volume:
Transactions of the Association for Computational Linguistics, Volume 4
Month:
Year:
2016
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
273–286
Language:
URL:
https://aclanthology.org/Q16-1020
DOI:
10.1162/tacl_a_00098
Bibkey:
Cite (ACL):
Tatsunori B. Hashimoto, David Alvarez-Melis, and Tommi S. Jaakkola. 2016. Word Embeddings as Metric Recovery in Semantic Spaces. Transactions of the Association for Computational Linguistics, 4:273–286.
Cite (Informal):
Word Embeddings as Metric Recovery in Semantic Spaces (Hashimoto et al., TACL 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/Q16-1020.pdf