Napredna pretraga

Pregled bibliografske jedinice broj: 792831

Proceedings of VarDial: Applying NLP Tools to Similar Languages, Varieties and Dialects


Proceedings of VarDial: Applying NLP Tools to Similar Languages, Varieties and Dialects, Dublin, Irska: Association for Computational Linguistics and Dublin City University, 2014 (zbornik)


Naslov
Proceedings of VarDial: Applying NLP Tools to Similar Languages, Varieties and Dialects

Urednik/ci
Zampieri, Marcos ; Tan, Liling ; Ljubešić, Nikola ; Tiedemann, Jörg

Vrsta, podvrsta i kategorija knjige
Uredničke knjige, zbornik, znanstvena

Izdavač
Association for Computational Linguistics and Dublin City University

Grad
Dublin, Irska

Godina
2014

Stranica
161

ISBN
978-1-873769-39-3

Ključne riječi
Natural language processing; similar languages; varieties; dialects

Sažetak
The interest in language resources and computational models for the study of similar languages, varieties and dialects has been growing substantially in the last few years. The first edition of the Workshop on Applying NLP tools to similar languages, varieties and dialects (VarDial) confirms the interest in the topic. Within the NLP community, the impact of language variation in the development of language resources and NLP applications has been explored in recent years with experiments in different directions. For example, automatic classification or identification of closely related languages such as in Huang and Lee (2008) and Tiedemann and Ljubešic ́ (2012) ; corpus-driven studies focusing on lexical variation between varieties such as the one by Piersman et al. (2010) or Ljubešic ́ and Fišer (2013) ; and finally, the adaptation of language models in the context of machine translation such as in Nakov and Tiedemann (2012). Together with the VarDial workshop we organized the Discriminating between Similar Languages (DSL) shared task. Discriminating between similar languages and language varieties is one of the bottlenecks of state-of-the-art language identification and it has been topic of a number of papers published in the last years. The DSL shared task provided a dataset to evaluate system’s performance on discriminating 13 different languages in 6 groups of languages. The 18 papers that appear in this volume deal with different NLP tasks and applications such as parsing, morphological analysis, part-of-speech tagging, language identification and speech recognition. The VarDial workshop received 18 submissions and 12 of them are published in this volume. The DSL shared task received 22 inscriptions and 8 final submissions. Five system description papers plus the DSL shared task report appear in this volume. We take this opportunity to thank the VarDial program committee who thoroughly reviewed all papers ; the DSL shared task participants for valuable feedback and discussions ; and the COLING organizers for their support, specially Jennifer Foster who replied promptly to all our inquiries.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti



POVEZANOST RADA


Ustanove
Filozofski fakultet, Zagreb

Autor s matičnim brojem:
Nikola Ljubešić, (272820)