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.

• Type: Conference
• Year: 2005
• Where: ECML
• Authors: Steffen Bickel, Peter Haider, Tobias Scheffer
• Keywords: Application-specific Document Collections, ECML 2005, Initial Text Fragment, N-gram Based Completion