Napredna pretraga

Pregled bibliografske jedinice broj: 914740

Evaluation of Language Models over Croatian Newspaper Texts


Beliga, Slobodan; Ipšić, Ivo; Martinčić-Ipšić, Sanda
Evaluation of Language Models over Croatian Newspaper Texts // Information Technology and Control, 46 (2017), 4; 425-444 doi:10.5755/j01.itc.46.4.18367 (međunarodna recenzija, članak, znanstveni)


Naslov
Evaluation of Language Models over Croatian Newspaper Texts

Autori
Beliga, Slobodan ; Ipšić, Ivo ; Martinčić-Ipšić, Sanda

Izvornik
Information Technology and Control (1392-124X) 46 (2017), 4; 425-444

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Statistical language model ; Natural language regularity ; Word-based language model ; Category-based language model ; Brown algorithm ; POS class ; N-gram ; Perplexity ; Croatian corpora

Sažetak
Statistical language modeling involves techniques and procedures that assign probabilities to word sequences or, said in other words, estimate the regularity of the language. This paper presents basic characteristics of statistical language models, reviews their use in the large set of speech and language applications, explains their formal definition and shows different types of language models. Detailed overview of n-gram and class- based models (as well as their combinations) is given chronologically, by type and complexity of models, and in aspect of their use in different NLP applications for different natural languages. The proposed experimental procedure compares three different types of statistical language models: n-gram models based on words, categorical models based on automatically determined categories and categorical models based on POS tags. In the paper, we propose a language model for contemporary Croatian texts, a procedure how to determine the best n-gram and the optimal number of categories, which leads to significant decrease of language model perplexity, estimated from the Croatian News Agency articles (HINA) corpus. Using different language models estimated from the HINA corpus, we show experimentally that models based on categories contribute to a better description of the natural language than those based on words. These findings of the proposed experiment are applicable, except for Croatian, for similar highly inflectional languages with rich morphology and non-mandatory sentence word order.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti



POVEZANOST RADA


Ustanove
Sveučilište u Rijeci - Odjel za informatiku

Časopis indeksira:


  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Citati