Title
Induction of fine-grained part-of-speech taggers via classifier combination and crosslingual projection
Abstract
This paper presents an original approach to part-of-speech tagging of fine-grained features (such as case, aspect, and adjective person/number) in languages such as English where these properties are generally not morphologically marked. The goals of such rich lexical tagging in English are to provide additional features for word alignment models in bilingual corpora (for statistical machine translation), and to provide an information source for part-of-speech tagger induction in new languages via tag projection across bilingual corpora. First, we present a classifier-combination approach to tagging English bitext with very fine-grained part-of-speech tags necessary for annotating morphologically richer languages such as Czech and French, combining the extracted features of three major English parsers, and achieve fine-grained-tag-level syntactic analysis accuracy higher than any individual parser. Second, we present experimental results for the cross-language projection of part-of-speech taggers in Czech and French via word-aligned bitext, achieving successful fine-grained part-of-speech tagging of these languages without any Czech or French training data of any kind.
Year
Venue
Keywords
2005
ParallelText@ACL
fine-grained part-of-speech taggers,successful fine-grained part-of-speech,crosslingual projection,part-of-speech tagger induction,fine-grained part-of-speech tag,classifier combination,major english parsers,french training data,bilingual corpus,fine-grained feature,part-of-speech taggers,classifier-combination approach,english bitext,part of speech
Field
DocType
Volume
Training set,Czech,Computer science,Machine translation,Part of speech,Speech recognition,Artificial intelligence,Natural language processing,Parsing,Classifier (linguistics),Adjective
Conference
W05-08
Citations 
PageRank 
References 
3
0.57
14
Authors
2
Name
Order
Citations
PageRank
Elliott Franco Drábek120616.02
David Yarowsky23986618.81