TY  - JOUR
AU  - Pajić, Vesna
AU  - Vitas, Duško
AU  - Pavlović-Lažetić, Gordana
AU  - Pajić, Miloš
PY  - 2013
UR  - http://aspace.agrif.bg.ac.rs/handle/123456789/3275
AB  - This paper presents a software system called WebMonitoring. The system is designed for solving certain problems in the process of information search on the web. The first problem is improving entering of queries at search engines and enabling more complex searches than keyword-based ones. The second problem is providing access to web page content that is inaccessible by common search engines due to search engine’s crawling limitations or time difference between the moment a web page is set up on the Internet and the moment the crawler finds it. The architecture of the WebMonitoring system relies upon finite state machines and the concept of monitoring the web. We present the system’s architecture and usage. Some modules were originally developed for the purpose of the WebMonitoring system, and some rely on UNITEX, linguistically oriented software system. We hereby evaluate the WebMonitoring system and give directions for further development.
PB  - ComSIS Consortium
T2  - Computer Science and Information Systems
T1  - WebMonitoring software system: Finite state machines for monitoring the web
EP  - 23
IS  - 1
SP  - 1
VL  - 10
DO  - 10.2298/CSIS110918036P
ER  - 

@article{
author = "Pajić, Vesna and Vitas, Duško and Pavlović-Lažetić, Gordana and Pajić, Miloš",
year = "2013",
abstract = "This paper presents a software system called WebMonitoring. The system is designed for solving certain problems in the process of information search on the web. The first problem is improving entering of queries at search engines and enabling more complex searches than keyword-based ones. The second problem is providing access to web page content that is inaccessible by common search engines due to search engine’s crawling limitations or time difference between the moment a web page is set up on the Internet and the moment the crawler finds it. The architecture of the WebMonitoring system relies upon finite state machines and the concept of monitoring the web. We present the system’s architecture and usage. Some modules were originally developed for the purpose of the WebMonitoring system, and some rely on UNITEX, linguistically oriented software system. We hereby evaluate the WebMonitoring system and give directions for further development.",
publisher = "ComSIS Consortium",
journal = "Computer Science and Information Systems",
title = "WebMonitoring software system: Finite state machines for monitoring the web",
pages = "23-1",
number = "1",
volume = "10",
doi = "10.2298/CSIS110918036P"
}

Pajić, V., Vitas, D., Pavlović-Lažetić, G.,& Pajić, M.. (2013). WebMonitoring software system: Finite state machines for monitoring the web. in Computer Science and Information Systems
ComSIS Consortium., 10(1), 1-23.
https://doi.org/10.2298/CSIS110918036P

Pajić V, Vitas D, Pavlović-Lažetić G, Pajić M. WebMonitoring software system: Finite state machines for monitoring the web. in Computer Science and Information Systems. 2013;10(1):1-23.
doi:10.2298/CSIS110918036P .

Pajić, Vesna, Vitas, Duško, Pavlović-Lažetić, Gordana, Pajić, Miloš, "WebMonitoring software system: Finite state machines for monitoring the web" in Computer Science and Information Systems, 10, no. 1 (2013):1-23,
https://doi.org/10.2298/CSIS110918036P . .

TY  - JOUR
AU  - Pajić, Vesna S.
AU  - Pavlović-Lažetić, Gordana
AU  - Beljanski, Milos V.
AU  - Brandt, Bernd W.
AU  - Pajić, Miloš
PY  - 2013
UR  - http://aspace.agrif.bg.ac.rs/handle/123456789/3280
AB  - To associate phenotypic characteristics of an organism to molecules encoded by its genome, there is a need for well-structured genotype and phenotype data. We use a novel method for extracting data on phenotype and genotype characteristics of microorganisms from text. As a resource, we use an encyclopedia of microorganisms, which holds phenotypic and genotypic data and create a structured, flexible data resource, which can be exported to a range of database formats, containing genotype and phenotype data for 2412 species and 873 genera of microbes. This data source has great potential as a resource for future biological research on genotype-phenotype associations. In this paper, we focus on describing the structure and content of the resulting database and on evaluating the method used for extracting the data. We conclude that the resulting database can be used as a reliable complementary resource for research into genotype-phenotype association.
PB  - Inderscience Enterprises Ltd, Geneva
T2  - International Journal of Data Mining and Bioinformatics
T1  - Towards a database for genotype-phenotype association research: mining data from encyclopaedia
EP  - 213
IS  - 2
SP  - 196
VL  - 7
DO  - 10.1504/IJDMB.2013.053196
ER  - 

@article{
author = "Pajić, Vesna S. and Pavlović-Lažetić, Gordana and Beljanski, Milos V. and Brandt, Bernd W. and Pajić, Miloš",
year = "2013",
abstract = "To associate phenotypic characteristics of an organism to molecules encoded by its genome, there is a need for well-structured genotype and phenotype data. We use a novel method for extracting data on phenotype and genotype characteristics of microorganisms from text. As a resource, we use an encyclopedia of microorganisms, which holds phenotypic and genotypic data and create a structured, flexible data resource, which can be exported to a range of database formats, containing genotype and phenotype data for 2412 species and 873 genera of microbes. This data source has great potential as a resource for future biological research on genotype-phenotype associations. In this paper, we focus on describing the structure and content of the resulting database and on evaluating the method used for extracting the data. We conclude that the resulting database can be used as a reliable complementary resource for research into genotype-phenotype association.",
publisher = "Inderscience Enterprises Ltd, Geneva",
journal = "International Journal of Data Mining and Bioinformatics",
title = "Towards a database for genotype-phenotype association research: mining data from encyclopaedia",
pages = "213-196",
number = "2",
volume = "7",
doi = "10.1504/IJDMB.2013.053196"
}

Pajić, V. S., Pavlović-Lažetić, G., Beljanski, M. V., Brandt, B. W.,& Pajić, M.. (2013). Towards a database for genotype-phenotype association research: mining data from encyclopaedia. in International Journal of Data Mining and Bioinformatics
Inderscience Enterprises Ltd, Geneva., 7(2), 196-213.
https://doi.org/10.1504/IJDMB.2013.053196

Pajić VS, Pavlović-Lažetić G, Beljanski MV, Brandt BW, Pajić M. Towards a database for genotype-phenotype association research: mining data from encyclopaedia. in International Journal of Data Mining and Bioinformatics. 2013;7(2):196-213.
doi:10.1504/IJDMB.2013.053196 .

Pajić, Vesna S., Pavlović-Lažetić, Gordana, Beljanski, Milos V., Brandt, Bernd W., Pajić, Miloš, "Towards a database for genotype-phenotype association research: mining data from encyclopaedia" in International Journal of Data Mining and Bioinformatics, 7, no. 2 (2013):196-213,
https://doi.org/10.1504/IJDMB.2013.053196 . .

TY  - CONF
AU  - Pajić, Vesna
AU  - Pavlović-Lažetić, Gordana
AU  - Pajić, Miloš
PY  - 2011
UR  - http://aspace.agrif.bg.ac.rs/handle/123456789/2415
AB  - The paper presents a new method for extracting information from semi-structured resources, based on finite state transducers. The method has two clearly distinguished phases. The first phase - pre-processing phase strongly relies upon the analysis of the document structure and it is used for locating records of data in the text. The second phase is based on the finite state transducers created for extracting information. The transducers can be modified so that preferred efficiency is achieved and can be reused for extracting information from other pre-processed documents. We conclude that even untagged text can be treated as a semi-structured one, providing its structure can be successfully pre-processed. As a result, we extracted data from free form encyclopedia text and created a fully structured database with genotype and phenotype characteristics of the organisms.
PB  - 16th International Conference on Implementation and Application of Automata, CIAA 2011
C3  - Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and
T1  - Information Extraction from Semi-structured Resources: A Two-Phase Finite State Transducers Approach
EP  - 289
SP  - 282
VL  - 6807 LNCS
DO  - 10.1007/978-3-642-22256-6_26
ER  - 

@conference{
author = "Pajić, Vesna and Pavlović-Lažetić, Gordana and Pajić, Miloš",
year = "2011",
abstract = "The paper presents a new method for extracting information from semi-structured resources, based on finite state transducers. The method has two clearly distinguished phases. The first phase - pre-processing phase strongly relies upon the analysis of the document structure and it is used for locating records of data in the text. The second phase is based on the finite state transducers created for extracting information. The transducers can be modified so that preferred efficiency is achieved and can be reused for extracting information from other pre-processed documents. We conclude that even untagged text can be treated as a semi-structured one, providing its structure can be successfully pre-processed. As a result, we extracted data from free form encyclopedia text and created a fully structured database with genotype and phenotype characteristics of the organisms.",
publisher = "16th International Conference on Implementation and Application of Automata, CIAA 2011",
journal = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and",
title = "Information Extraction from Semi-structured Resources: A Two-Phase Finite State Transducers Approach",
pages = "289-282",
volume = "6807 LNCS",
doi = "10.1007/978-3-642-22256-6_26"
}

Pajić, V., Pavlović-Lažetić, G.,& Pajić, M.. (2011). Information Extraction from Semi-structured Resources: A Two-Phase Finite State Transducers Approach. in Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and
16th International Conference on Implementation and Application of Automata, CIAA 2011., 6807 LNCS, 282-289.
https://doi.org/10.1007/978-3-642-22256-6_26

Pajić V, Pavlović-Lažetić G, Pajić M. Information Extraction from Semi-structured Resources: A Two-Phase Finite State Transducers Approach. in Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and. 2011;6807 LNCS:282-289.
doi:10.1007/978-3-642-22256-6_26 .

Pajić, Vesna, Pavlović-Lažetić, Gordana, Pajić, Miloš, "Information Extraction from Semi-structured Resources: A Two-Phase Finite State Transducers Approach" in Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and, 6807 LNCS (2011):282-289,
https://doi.org/10.1007/978-3-642-22256-6_26 . .