Learning to Complete Sentences

Abstract

We consider the problem of predicting how a user will continue a given initial text fragment. Intuitively, our goal is to develop a “tab-complete” function for natural language, based on a model that is learned from text data. We consider two learning mechanisms that generate predictive models from collections of application-specific document collections: we develop an N -gram based completion method and discuss the application of instance-based learning. After developing evaluation metrics for this task, we empirically compare the model-based to the instance-based method and assess the predictability of call-center emails, personal emails, and weather reports.

Cite

Text

Bickel et al. "Learning to Complete Sentences." European Conference on Machine Learning, 2005. doi:10.1007/11564096_47

Markdown

[Bickel et al. "Learning to Complete Sentences." European Conference on Machine Learning, 2005.](https://mlanthology.org/ecmlpkdd/2005/bickel2005ecml-learning/) doi:10.1007/11564096_47

BibTeX

@inproceedings{bickel2005ecml-learning,
  title     = {{Learning to Complete Sentences}},
  author    = {Bickel, Steffen and Haider, Peter and Scheffer, Tobias},
  booktitle = {European Conference on Machine Learning},
  year      = {2005},
  pages     = {497-504},
  doi       = {10.1007/11564096_47},
  url       = {https://mlanthology.org/ecmlpkdd/2005/bickel2005ecml-learning/}
}