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

Basit Öğe Kaydı
dc.authorid0000-0002-4597-0954
dc.authorid0000-0002-9777-4613
dc.authorid0000-0001-5246-2117
dc.contributor.authorGüz, Ümiten_US
dc.contributor.authorFavre, Benoiten_US
dc.contributor.authorHakkani Tür, Dileken_US
dc.contributor.authorTür, Gökhanen_US
dc.date.accessioned2015-01-15T23:01:18Z
dc.date.available2015-01-15T23:01:18Z
dc.date.issued2009-07
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Electrical-Electronics Engineeringen_US
dc.descriptionThis 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).en_US
dc.description.abstractThis 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.en_US
dc.description.sponsorshipCALOen_US
dc.description.sponsorshipDARPA GALEen_US
dc.description.sponsorshipICSIen_US
dc.description.sponsorshipIsik Universityen_US
dc.description.sponsorshipTUBITAKen_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationGüz, 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.2009.2016393en_US
dc.identifier.doi10.1109/TASL.2009.2016393
dc.identifier.endpage903
dc.identifier.issn1558-7916
dc.identifier.issn1558-7924
dc.identifier.issue5
dc.identifier.scopus2-s2.0-85008018937
dc.identifier.scopusqualityN/A
dc.identifier.startpage895
dc.identifier.urihttps://hdl.handle.net/11729/326
dc.identifier.urihttp://dx.doi.org/10.1109/TASL.2009.2016393
dc.identifier.volume17
dc.identifier.wosWOS:000267434300005
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakScience Citation Index Expanded (SCI-EXPANDED)en_US
dc.institutionauthorGüz, Ümiten_US
dc.institutionauthorid0000-0002-4597-0954
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherIEEE-INST Electrical Electronics Engineers Incen_US
dc.relation.ispartofIEEE Transactions on Audio Speech and Language Processingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectProsodic and lexical informationen_US
dc.subjectSentence segmentationen_US
dc.subjectTurkish morphologyen_US
dc.subjectAutomatic speech recognitionen_US
dc.subjectBoostingen_US
dc.subjectComputer scienceen_US
dc.subjectData miningen_US
dc.subjectFeature extractionen_US
dc.subjectHidden Markov modelsen_US
dc.subjectHybrid power systemsen_US
dc.subjectMorphologyen_US
dc.subjectNatural languagesen_US
dc.subjectVocabularyen_US
dc.subjectSpeech processingen_US
dc.subjectWord processingen_US
dc.subjectTurkish word sequencesen_US
dc.subjectConditional random fieldsen_US
dc.subjectDiscriminative classification techniquesen_US
dc.subjectDiscriminative methodsen_US
dc.subjectGenerative methodsen_US
dc.subjectHidden event language modelingen_US
dc.subjectMorphological informationen_US
dc.titleGenerative and discriminative methods using morphological information for sentence segmentation of Turkishen_US
dc.typeArticleen_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
326.pdf
Boyut:
626.12 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir

Koleksiyon

Makale Koleksiyonu | Elektrik-Elektronik Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu