Napredna pretraga

Pregled bibliografske jedinice broj: 348726

Investigating Language Independence in HMM PoS/MSD-Tagging


Agić, Željko; Tadić, Marko; Dovedan, Zdravko
Investigating Language Independence in HMM PoS/MSD-Tagging // Proceedings of the 30th International Conference on Information Technology Interfaces / Lužar-Stiffler, Vesna ; Hljuz Dobrić, Vesna ; Bekić, Zoran (ur.).
Zagreb: SRCE University Computer Centre, University of Zagreb, 2008. str. 657-662 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Investigating Language Independence in HMM PoS/MSD-Tagging

Autori
Agić, Željko ; Tadić, Marko ; Dovedan, Zdravko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 30th International Conference on Information Technology Interfaces / Lužar-Stiffler, Vesna ; Hljuz Dobrić, Vesna ; Bekić, Zoran - Zagreb : SRCE University Computer Centre, University of Zagreb, 2008, 657-662

ISBN
978-953-7138-12-7

Skup
30th International Conference on Information Technology Interfaces (ITI 2008)

Mjesto i datum
Cavtat / Dubrovnik, Hrvatska, 23-26.06.2008.

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Language independence; part-of-speech tagging; morphosyntactic tagging; hidden Markov models

Sažetak
The paper presents an investigation of functional dependencies in morphosyntactic tagging using hidden Markov models. Starting from a well known fact that the HMM tagging paradigm relies on lexical knowledge acquired from training corpora and stored in form of transition and emission matrices, also called a language model, in the experiment, we apply the TnT trigram tagger on creating language models for seven different languages from the MULTEXT East v3 project translations of George Orwell’ s 1984. – Czech, Estonian, Hungarian, Romanian, Serbian, Slovene and original English version. We then use these language models in the tagging procedure and obtain details on various relations between training corpora statistics, training outputs and outputs of the tagging procedure.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti, Filologija



POVEZANOST RADA


Projekt / tema
036-1300646-1986 - Otkrivanje znanja u tekstnim podacima (Bojana Dalbelo-Bašić, )
130-1300646-0645 - Hrvatski jezični resursi i njihovo obilježavanje (Marko Tadić, )
130-1300646-1776 - Računalna sintaksa hrvatskoga jezika (Zdravko Dovedan Han, )

Ustanove
Filozofski fakultet, Zagreb