Paper: Predicting Sentences Using N-Gram Language Models

ACL ID H05-1025
Title Predicting Sentences Using N-Gram Language Models
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

We explore the benefit that users in sev- eral application areas can experience from a “tab-complete” editing assistance func- tion. We develop an evaluation metric and adapt N-gram language models to the problem of predicting the subsequent words, given an initial text fragment. Us- ing an instance-based method as base- line, we empirically study the predictabil- ity of call-center emails, personal emails, weather reports, and cooking recipes.