From Czech Morphology through Partial Parsing to Disambiguation

Mráková, Eva; Sedláček, Radek

doi:10.1007/3-540-36456-0_13

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The full tag is replaced by the POS tag (the first two fields); there are 60 POS tags. The TM3 8 Czech morphological processing was studied by Petkevič (2001), Hlavácová (2001) (who focuses on handling OOV words), and Mráková and Sedlacek (2003) (who use partial parsing to reduce the set of possible analyses), inter alia. feature templates are included twice: once for the full tag and once for a coarser tag (the first PDT field, for which there are 12 possible values).…”

Section: Factored Tags and Estimationmentioning

confidence: 99%

Context-based morphological disambiguation with random fields

Smith

Tromble

2005

Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05

View full text Add to dashboard Cite

Finite-state approaches have been highly successful at describing the morphological processes of many languages. Such approaches have largely focused on modeling the phone-or character-level processes that generate candidate lexical types, rather than tokens in context. For the full analysis of words in context, disambiguation is also required (Hakkani-Tür et al., 2000;Hajič et al., 2001). In this paper, we apply a novel source-channel model to the problem of morphological disambiguation (segmentation into morphemes, lemmatization, and POS tagging) for concatenative, templatic, and inflectional languages. The channel model exploits an existing morphological dictionary, constraining each word's analysis to be linguistically valid. The source model is a factored, conditionally-estimated random field (Lafferty et al., 2001) that learns to disambiguate the full sentence by modeling local contexts. Compared with baseline state-of-the-art methods, our method achieves statistically significant error rate reductions on Korean, Arabic, and Czech, for various training set sizes and accuracy measures.

show abstract

Section: Factored Tags and Estimationmentioning

confidence: 99%