×

Part-of-speech tagging with two sequential transducers. (English) Zbl 0989.68556

Yu, Sheng (ed.) et al., Implementation and application of automata. 5th international conference, CIAA 2000, London, Ontario, Canada, July 24-25, 2000. Revised papers. Berlin: Springer. Lect. Notes Comput. Sci. 2088, 337-339 (2001).
Summary: We present a method of constructing and using a cascade consisting of a left- and a right-sequential finite-state transducer (FST), \(T_2\) and \(T_2\), for part-of-speech (POS) disambiguation. Compared to a Hidden Markov model (HMM), this FST cascade has the advantage of significantly higher processing speed, but at the cost of slightly lower accuracy. Applications such as Information Retrieval, where the speed can be more important than accuracy, could benefit from this approach.
For the entire collection see [Zbl 0968.00056].

MSC:

68U99 Computing methodologies and applications
68Q45 Formal languages and automata
68T50 Natural language processing

Software:

MBT
PDFBibTeX XMLCite
Full Text: Link