You are here

Part-of-Speech Tagging Using Parallel Weighted Finite-State Transducers

TitlePart-of-Speech Tagging Using Parallel Weighted Finite-State Transducers
Publication TypeBook Chapter
Year of Publication2010
AuthorsSilfverberg, M, Lindén, K
EditorLoftsson, H, Rögnvaldsson, E, Helgadóttir, S
Book TitleAdvances in Natural Language Processing
Series TitleLecture Notes in Computer Science
Volume6233
Pagination369-380
PublisherSpringer
CityBerlin / Heidelberg
ISBN978-3-642-14769-2
Keywordsmarkov model, part-of-speech tagging, weighted finite-state transducer
Abstract

We use parallel weighted finite-state transducers to implement a part-of-speech tagger, which obtains state-of-the-art accuracy when used to tag the Europarl corpora for Finnish, Swedish and English. Our system consists of a weighted lexicon and a guesser combined with a bigram model factored into two weighted transducers. We use both lemmas and tag sequences in the bigram model, which guarantees reliable bigram estimates.

DOI10.1007/978-3-642-14770-8_40