Learning Features from Co-occurrences: A Theoretical Analysis

Yanpeng Li


Abstract
Representing a word by its co-occurrences with other words in context is an effective way to capture the meaning of the word. However, the theory behind remains a challenge. In this work, taking the example of a word classification task, we give a theoretical analysis of the approaches that represent a word X by a function f(P(C|X)), where C is a context feature, P(C|X) is the conditional probability estimated from a text corpus, and the function f maps the co-occurrence measure to a prediction score. We investigate the impact of context feature C and the function f . We also explain the reasons why using the co-occurrences with multiple context features may be better than just using a single one. In addition, based on the analysis, we propose a hypothesis about the conditional probability on zero probability events.
Anthology ID:
C18-1241
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2846–2854
Language:
URL:
https://aclanthology.org/C18-1241
DOI:
Bibkey:
Cite (ACL):
Yanpeng Li. 2018. Learning Features from Co-occurrences: A Theoretical Analysis. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2846–2854, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Learning Features from Co-occurrences: A Theoretical Analysis (Li, COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/C18-1241.pdf