Paper: Automatic Animacy Classification

ACL ID N12-2002
Title Automatic Animacy Classification
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Student Session
Year 2012

We introduce the automatic annotation of noun phrases in parsed sentences with tags from a fine-grained semantic animacy hierar- chy. This information is of interest within lex- ical semantics and has potential value as a fea- ture in several NLP tasks. We train a discriminative classifier on an an- notated corpus of spoken English, with fea- tures capturing each noun phrase?s constituent words, its internal structure, and its syntactic relations with other key words in the sentence. Only the first two of these three feature sets have a substantial impact on performance, but the resulting model is able to fairly accurately classify new data from that corpus, and shows promise for binary animacy classification and for use on automatically parsed text.