Part-of-speech tagging with neural networks

Text corpora which are tagged with part-ofspeech information are useful in many areas of linguistic research. In this paper, a new partof -speech tagging method based on neural networks (Net-Tagger) is presented and its performance is compared to that of a HMM-tagger CKPS92 and a trigram-based tagger Kem93. It is shown that the Net-Tagger performs as well as the trigram-based tagger and better than the HMM-tagger. 2 Introduction Words are often ambiguous in their part of speech. The English word store for example can be either a noun, a finite verb or an infinitive. In an utterance, this ambiguity is normally resolved by the context of a word: e.g. in the sentence The 1977 PCs could store two pages of data., store can only be an infinitive. A part-of-speech tagger is a system which automatically assigns the part of speech to words using contextual information. Potential applications for part-of-speech taggers exist in many areas including speech recognition, speech syn- Thi...