no code implementations • 8 May 2014 • Kristina Ban, Ana Meštrović, Sanda Martinčić-Ipšić
This paper presents preliminary results of Croatian syllable networks analysis.
no code implementations • 12 May 2014 • Sabina Šišović, Sanda Martinčić-Ipšić, Ana Meštrović
The linguistic networks are constructed from texts as directed and weighted co-occurrence networks of words.
no code implementations • 15 May 2014 • Domagoj Margan, Ana Meštrović, Sanda Martinčić-Ipšić
Additionally, in the first shuffling approach we preserved the sentence structure of the text and the number of words per sentence.
no code implementations • 17 May 2014 • Domagoj Margan, Sanda Martinčić-Ipšić, Ana Meštrović
Finally, since the size of texts is reflected in the network properties, our results suggest that the corpus influence can be reduced by increasing the co-occurrence window size.
no code implementations • 14 Jul 2014 • Sabina Šišović, Sanda Martinčić-Ipšić, Ana Meštrović
In this paper we analyse the selectivity measure calculated from the complex network in the task of the automatic keyword extraction.
no code implementations • 17 Jul 2014 • Slobodan Beliga, Ana Meštrović, Sanda Martinčić-Ipšić
Obtained sets are evaluated on a manually annotated keywords: for the set of extracted keyword candidates average F1 score is 24, 63%, and average F2 score is 21, 19%; for the exacted words-tuples candidates average F1 score is 25, 9% and average F2 score is 24, 47%.
no code implementations • 28 Aug 2014 • Slobodan Beliga, Sanda Martinčić-Ipšić
This paper presents categorization of Croatian texts using Non-Standard Words (NSW) as features.
no code implementations • 18 Nov 2014 • Hana Rizvić, Sanda Martinčić-Ipšić, Ana Meštrović
Firstly, we show that the triad significance profile for the Croatian language is very similar with the other languages and all the networks belong to the same family of networks.
no code implementations • 27 Mar 2015 • Slobodan Beliga, Miran Pobar, Sanda Martinčić-Ipšić
This paper presents text normalization which is an integral part of any text-to-speech synthesis system.
no code implementations • 30 Jul 2015 • Domagoj Margan, Ana Meštrović, Sanda Martinčić-Ipšić
The multilayer network of language is a unified framework for modeling linguistic subsystems and their structural properties enabling the exploration of their mutual interactions.
no code implementations • 5 Jul 2017 • Sanda Martinčić-Ipšić, Tanja Miličić, Ljupčo Todorovski
In this study, we measure the performance of the document classifiers trained using the method of random forests for features generated the three models and their variants.