Generative and discriminative methods using morphological information for sentence segmentation of Turkish

Yükleniyor...
Küçük Resim

Tarih

2009-07

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

IEEE-INST Electrical Electronics Engineers Inc

Erişim Hakkı

info:eu-repo/semantics/closedAccess

Araştırma projeleri

Organizasyon Birimleri

Dergi sayısı

Özet

This paper presents novel methods for generative, discriminative, and hybrid sequence classification for segmentation of Turkish word sequences into sentences. In the literature, this task is generally solved using statistical models that take advantage of lexical information among others. However, Turkish has a productive morphology that generates a very large vocabulary, making the task much harder. In this paper, we introduce a new set of morphological features, extracted from words and their morphological analyses. We also extend the established method of hidden event language modeling (HELM) to factored hidden event language modeling (fHELM) to handle morphological information. In order to capture non-lexical information, we extract a set of prosodic features, which are mainly motivated from our previous work for other languages. We then employ discriminative classification techniques, boosting and conditional random fields (CRFs), combined with fHELM, for the task of Turkish sentence segmentation.

Açıklama

This material is based upon work supported by the Defense Advanced Research Projects Agency (DARPA) CALO (NBCHD-030010) program, the DARPA GALE (HR0011-06-C-0023) program, the Scientific and Technological Research Council of Turkey (TUBITAK) fundings at SRI and ICSI, (TUBITAK CAREER Project 107E182, Extracting and Using Prosodic Information for Turkish Spoken Language), and the Isik University Research Fund (Project 05B304).

Anahtar Kelimeler

Prosodic and lexical information, Sentence segmentation, Turkish morphology, Automatic speech recognition, Boosting, Computer science, Data mining, Feature extraction, Hidden Markov models, Hybrid power systems, Morphology, Natural languages, Vocabulary, Speech processing, Word processing, Turkish word sequences, Conditional random fields, Discriminative classification techniques, Discriminative methods, Generative methods, Hidden event language modeling, Morphological information

Kaynak

IEEE Transactions on Audio Speech and Language Processing

WoS Q Değeri

Q2
Q2

Scopus Q Değeri

N/A

Cilt

17

Sayı

5

Künye

Güz, Ü., Favre, B., Hakkani Tür, D. & Tür, G. (2009). Generative and discriminative methods using morphological information for sentence segmentation of turkish. IEEE Transactions on Audio, Speech, and Language Processing, 17(5), 895-903. doi:10.1109/TASL.2009.2016393