Paper: Prototype-Driven Learning For Sequence Models

ACL ID N06-1041
Title Prototype-Driven Learning For Sequence Models
Venue Human Language Technologies
Session Main Conference
Year 2006

We investigate prototype-driven learning for pri- marily unsupervised sequence modeling. Prior knowledge is specified declaratively, by provid- ing a few canonical examples of each target an- notation label. This sparse prototype information is then propagated across a corpus using distri- butional similarity features in a log-linear gener- ative model. On part-of-speech induction in En- glishandChinese,aswellasaninformationextrac- tion task, prototypefeaturesprovide substantialer- ror rate reductions over competitive baselines and outperform previous work. For example, we can achieveanEnglishpart-of-speechtaggingaccuracy of 80.5% using only three examples of each tag and no dictionaryconstraints. We also compareto semi-supervisedlearning and discuss the system’s errortrends.