ML Anthology

Local Likelihood Modeling of Temporal Text Streams

Guy Lebanon, Yang Zhao
ICML 2008 pp. 552-559
doi:10.1145/1390156.1390226 /icml/2008/lebanon2008icml-local/

Abstract

Temporal text data is often generated by a time-changing process or distribution. Such a drift in the underlying distribution cannot be captured by stationary likelihood techniques. We consider the application of local likelihood methods to generative and conditional modeling of temporal document sequences. We examine the asymptotic bias and variance and present an experimental study using the RCV1 dataset containing a temporal sequence of Reuters news stories.

PDF ICML Semantic Scholar

Cite

Text

Lebanon and Zhao. "Local Likelihood Modeling of Temporal Text Streams." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390226

Markdown

[Lebanon and Zhao. "Local Likelihood Modeling of Temporal Text Streams." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/lebanon2008icml-local/) doi:10.1145/1390156.1390226

BibTeX

@inproceedings{lebanon2008icml-local,
  title     = {{Local Likelihood Modeling of Temporal Text Streams}},
  author    = {Lebanon, Guy and Zhao, Yang},
  booktitle = {International Conference on Machine Learning},
  year      = {2008},
  pages     = {552-559},
  doi       = {10.1145/1390156.1390226},
  url       = {https://mlanthology.org/icml/2008/lebanon2008icml-local/}
}