2011 19thTelecommunications Forum (TELFOR) Proceedings of Papers 2011
DOI: 10.1109/telfor.2011.6143778
|View full text |Cite
|
Sign up to set email alerts
|

A software system for determining the semantic similarity of short texts in Serbian

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
3
0
1

Year Published

2019
2019
2023
2023

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 0 publications
0
3
0
1
Order By: Relevance
“…Smatra se da je dozvoljena, Apache licenca ne zahteva da se modifikacije ili izvedena dela distribuiraju pod istom licencom kao original. Informacije o originalnoj licenci moraju biti sačuvane za neizmenjene delove, a osim ako nije eksplicitno navedeno, izmenjeni delovi su automatski pod Apache licencom (Batanović, 2011). Licenca dozvoljava dodelu dodatnih prava koja nisu uključena u originalnu licencu trećim licima (Rstić, 2020).…”
Section: Tipovi Licenci Otvorenog Koda I Njihova Upotrebaunclassified
“…Smatra se da je dozvoljena, Apache licenca ne zahteva da se modifikacije ili izvedena dela distribuiraju pod istom licencom kao original. Informacije o originalnoj licenci moraju biti sačuvane za neizmenjene delove, a osim ako nije eksplicitno navedeno, izmenjeni delovi su automatski pod Apache licencom (Batanović, 2011). Licenca dozvoljava dodelu dodatnih prava koja nisu uključena u originalnu licencu trećim licima (Rstić, 2020).…”
Section: Tipovi Licenci Otvorenog Koda I Njihova Upotrebaunclassified
“…Sentences from online press sources were collected for The Serbian Corpus of Paraphrases (paraphrase.sr, Table 2). A binary similarity score was manually assigned to each pair of sentences, indicating whether the sentences in the pair are semantically similar enough to be considered close paraphrases (Batanović et al, 2011). Another corpus for determining semantic similarity, The Serbian Corpus of Short News Texts -(STS.news.sr, Table 2), consists of 1192 pairs of sentences in Serbian that were collected from news sources on the internet .…”
Section: Monolingual Corporamentioning
confidence: 99%
“…In our research, for the purpose of stemming, we relied on the open source implementation of a collection of stemmers for the Serbian and Croatian language, the work of Vuk Batanović [3]. The delivered library, written in the Java program language, among other things enables the processing of content of textual data files from the command line, using the following command: java -jar SCStemmers.jar StemmerID InputFile OutputFile where the StemmerID is the number of the appropriate algorithm:…”
Section: Stemmingmentioning
confidence: 99%