Paper: Automatic Article Restoration

ACL ID N04-2006
Title Automatic Article Restoration
Venue Human Language Technologies
Session Student Session
Year 2004
  • John Lee (Massachusetts Institute of Technology, Cambridge MA)

One common mistake made by non-native speakers of English is to drop the articles a, an, or the. We apply the log-linear model to auto- matically restore missing articles based on fea- tures of the noun phrase. We first show that the model yields competitive results in article gen- eration. Further, we describe methods to adjust the model with respect to the initial quality of the sentence. Our best results are 20.5% arti- cle error rate (insertions, deletions and substi- tutions) for sentences where 30% of the articles have been dropped, and 38.5% for those where 70% of the articles have been dropped.