Morpheme based Language Model for Tamil Part-of-Speech Tagging
Fuente:
Redalyc
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artículo científico |
| Sprache: | en |
| Veröffentlicht: |
Instituto Politécnico Nacional
2008
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1876424939815305216 |
|---|---|
| author | S. Lakshmana Pandian |
| author_facet | S. Lakshmana Pandian |
| contents | Morpheme based Language Model for Tamil Part-of-Speech Tagging S. Lakshmana Pandian T. V. Geetha Computación language model Bayesian learning morpheme components generalized iterative scaling The paper describes a Tamil Part of Speech (POS)tagging using a corpus-based approach by formulating aLanguage Model using morpheme components of words. Rulebased tagging, Markov model taggers, Hidden Markov Modeltaggers and transformation-based learning tagger are some of themethods available for part of speech tagging. In this paper, wepresent a language model based on the information of the stemtype, last morpheme, and previous to the last morpheme part ofthe word for categorizing its part of speech. For estimating thecontribution factors of the model, we follow generalized iterativescaling technique. Presented model has the overall F-measure of96%. 2008 artículo científico 1870-9044 https://www.redalyc.org/articulo.oa?id=402640451002 en http://www.redalyc.org/revista.oa?id=4026 Polibits application/pdf Instituto Politécnico Nacional Polibits (México) Vol.38 |
| format | Artículo científico |
| id | redalyc_402640451002 |
| institution | Redalyc |
| language | en |
| publishDate | 2008 |
| publisher | Instituto Politécnico Nacional |
| spellingShingle | Morpheme based Language Model for Tamil Part-of-Speech Tagging S. Lakshmana Pandian Computación language model Bayesian learning morpheme components generalized iterative scaling Morpheme based Language Model for Tamil Part-of-Speech Tagging S. Lakshmana Pandian T. V. Geetha Computación language model Bayesian learning morpheme components generalized iterative scaling The paper describes a Tamil Part of Speech (POS)tagging using a corpus-based approach by formulating aLanguage Model using morpheme components of words. Rulebased tagging, Markov model taggers, Hidden Markov Modeltaggers and transformation-based learning tagger are some of themethods available for part of speech tagging. In this paper, wepresent a language model based on the information of the stemtype, last morpheme, and previous to the last morpheme part ofthe word for categorizing its part of speech. For estimating thecontribution factors of the model, we follow generalized iterativescaling technique. Presented model has the overall F-measure of96%. 2008 artículo científico 1870-9044 https://www.redalyc.org/articulo.oa?id=402640451002 en http://www.redalyc.org/revista.oa?id=4026 Polibits application/pdf Instituto Politécnico Nacional Polibits (México) Vol.38 |
| title | Morpheme based Language Model for Tamil Part-of-Speech Tagging |
| topic | Computación language model Bayesian learning morpheme components generalized iterative scaling |
| url | https://www.redalyc.org/articulo.oa?id=402640451002 |