@InProceedings{li:2018:C18-1,
  author    = {Li, Yanpeng},
  title     = {Learning Features from Co-occurrences: A Theoretical Analysis},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  month     = {August},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {2846--2854},
  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.},
  url       = {http://www.aclweb.org/anthology/C18-1241}
}