Josef Steinberger


E-mail: jstein@kiv.zcu.cz

Josef is a researcher in Natural Language Processing. He is interested in media monitoring and analysis, from news to social media. Building media monitoring solutions results in working on news clustering and categorisation, story tracking, information extraction, named entity recognition, quote recognition, information visualisation and other text analysing applications. Research topics of his special interest include automatic text summarisation, sentiment analysis and coreference resolution. The goal is to build multilingual approaches by limiting dependency on a particular language or building multilingual resources.After his postdoc mission at Joint Research Centre of European Commission, where he worked on new functionality for Europe Media Monitor, he parked back at the University of West Bohemia to continue career as a lecturer.

Publications:


Sort by:Year | Title | Citations

Publication

Aspect-Driven News Summarization

Authors:  Josef Steinberger, Hristo Tanev, Mijail Alexandrov Kabadjov, Ralf Steinberger
Source:In: International Journal of Computational Linguistics and Applications 2 (1-2), ISSN: 0976-0962, Bahri Publications. 2011.
ISSN:0976-0962
Download: download Full text [225 kB]
Publication

Aspects of Multilingual News Summarisation

Authors:  Josef Steinberger, Hristo Tanev, Ralf Steinberger, Vanni Zavarella, Marco Turchi
Source:Steinberger, J., Tanev, H., Zavarella, V., Steinberger, R., Turchi, M. (2014): Aspects of Multilingual News Summarisation. In: Alessandro Fiori (ed.): Innovative Document Summarization Techniques: Revolutionizing Knowledge Understanding, Advances in Data Mining and Database Management series, pages 277-294, ISSN: 2327-1981, ISBN 978-1-4666-5019-0, DOI: 10.4018/978-1-4666-5019-0.ch012, IGI Global.
Download: download Full text [586 kB]
Publication

Automatic Text Summarization (The state of the art 2007 and new challenges)

Authors:  Karel Ježek, Josef Steinberger
Source:In Proceedings of Znalosti 2008, Bratislava, Slovakia, February 2008, pp. 1–12, ISBN 978-80-227-2827-0.
Download: download Full text [182 kB]
Publication

Challenges and solutions in the opinion summarization of user-generated content

Authors:  Alexandra Balahur, Mijail Alexandrov Kabadjov, Josef Steinberger, Ralf Steinberger, Andrés Montoyo
Source:In: Journal of Intelligent Information Systems 39(2), pages 375-398, ISSN: 0925-9902, DOI: 10.1007/s10844-011-0194-z, Springer. 2012.
ISSN:0925-9902
Download: download Full text 
View record in Web of Science®
Publication

Enhancing N-Gram-based Summary Evaluation Using Information Content and a Taxonomy

Authors:  Mijail Alexandrov Kabadjov, Josef Steinberger, Ralf Steinberger, Massimo Poesio, Bruno Pouliquen
Source:In: Advances in Information Retrieval, Lecture Notes in Computer Science 5993, pages 662-666, ISSN: 302-9743, DOI:10.1007/978-3-642-12275-0_71, Springer, 2010.
ISSN: 0302-9743
Download: download Full text 
View record in Web of Science®
Publication

Evaluation Measures for Text Summarization

Authors:  Josef Steinberger, Karel Ježek
Source:In Computing and Informatics, volume 28 (2009), number 2, pages 251-275, Slovak Academy of Sciences, ISSN 1335-9150.
ISSN:1335-9150
Download: download Full text 
View record in Web of Science®
Publication

Exploiting Higher-level Semantic Information for the Opinion-oriented Summarization of Blogs

Authors:  Alexandra Balahur, Mijail Alexandrov Kabadjov, Josef Steinberger
Source:In: International Journal of Computational Linguistics and Applications 1 (1-2), pages 45-59, ISSN: 0976-0962, Bahri Publications, 2010.
ISSN:0976-0962
Download: download Full text [2067 kB]
Publication

Exploration and Evaluation of Citation Networks

Authors:  Karel Ježek, Dalibor Fiala, Josef Steinberger
Source:Proceedings of the 12th International Conference on Electronic Publishing, ISBN 978-0-7727-6315-0, pp 351-362, Toronto, Canada 2008
Download: download Full text [110 kB]
Publication

Highly Multilingual Coreference Resolution Exploiting a Mature Entity Repository

Authors:  Josef Steinberger, Jenya  Belyaeva, Jonathan Crawley, Leonida Della-Rocca, Mohamed Ebrahim, Maud Ehrmann, Mijail Alexandrov Kabadjov, Ralf Steinberger, Erik var der Goot
Source:In: Proceedings of the 8th International Conference Recent Advances in Natural Language Processing, pages 254-260. Hissar, Bulgaria, 2011.
Download: download Full text 
Publication

Identifying Novel Information using Latent Semantic Analysis in the WiQA Task at CLEF 2006

Authors:  Richard F. E. Sutcliffe, Josef Steinberger, Udo Kruschwitz, Massimo Poesio, Mijail Alexandrov Kabadjov
Source:In Lecture Notes in Computer Science 4730, 2007, pp. 541-549, Springer-Verlag Berlin Heidelberg, ISSN 0302-9743, ISBN 978-3-540-74998-1.
ISSN:0302-9743
Download: download Full text 
View record in Web of Science®
Publication

Improving LSA-based Summarization with Anaphora Resolution

Authors:  Josef Steinberger, Mijail Alexandrov Kabadjov, Massimo Poesio
Source:In Proceedings of Human Language Technology Conference/Conference on Empirical Methods in Natural Language Processing, Vancouver, Canada, October 2005, pp. 1–8, The Association for Computational Linguistics, ISBN 1-932432-55-8.
Download: download Full text [95 kB]
Publication

In Czech: AktualizaÄní sumarizace textů

Authors:  Josef Steinberger
Source:In Proceedings of Znalosti 2009, Brno, Czech Republic, February 2009, pp. 234–245, ISBN 978-80-227-3015-0.
Publication

In Czech: Hodnocení kvality sumarizátorů textů

Authors:  Josef Steinberger, Karel Ježek
Source:In Proceedings of Znalosti 2005 Conference, Stará Lesná, Slovakia, February 2005, pp. 96–107, ISBN 80-248-0755-6.
Download: download Full text [338 kB]
Publication

In Czech: Sumarizace textů

Authors:  Karel Ježek, Josef Steinberger
Source:Proceedings of Annual Database Conference DATAKON, October 16-19, 2010, Mikulov, Czech Rep., pp.3-23, ISBN 978-80-7368-424-2
Download: download Full text [194 kB]
Publication

JRC’s Participation in the Guided Summarization Task at TAC 2010

Authors:  Josef Steinberger, Hristo Tanev, Mijail Alexandrov Kabadjov, Ralf Steinberger
Source:In: Proceedings of the Text Analysis Conference 2010, National Institute of Standards and Technology (NIST). Gaithersburg, USA, 2011.
Download: download Full text 
Publication

JRC’s Participation at TAC 2011: Guided and Multilingual Summarization Tasks

Authors:  Josef Steinberger, Mijail Alexandrov Kabadjov, Ralf Steinberger, Hristo Tanev, Marco Turchi, Vanni Zavarella
Source:In: Proceedings of the Text Analysis Conference 2011, National Institute of Standards and Technology (NIST). Gaithersburg, USA, 2012.
Download: download Full text 
Publication

Knowledge-poor Multilingual Sentence Compression

Authors:  Josef Steinberger, Roman TesaÅ™
Source:In Proceedings of 7th Conference on Language Engineering, Cairo, Egypt, December 2007, pp. 369-379, The Egyptian Society of Language Engineering.
Download: download Full text [226 kB]
Publication

LSA-Based Multi-Document Summarization

Authors:  Josef Steinberger, Martin KÅ™iÅ¡Å¥an
Source:In Proceedings of 8th International PhD Workshop on Systems and Control, a Young Generation Viewpoint, Balatonfured, Hungary, September 2007, pp. 87-91, ISBN 978-963-311-365-3.
Download: download Full text [87 kB]
Publication

Machine Translation for Multilingual Summary Content Evaluation

Authors:  Josef Steinberger, Marco Turchi
Source:In: Proceedings of the NAACL Workshop on Evaluation Metrics and System Comparison for Automatic Summarization, pages 19-27, ACL. Montreal, Canada, 2012.
Download: download Full text 
Publication

Multi-document multilingual summarization corpus preparation, Part 2: Czech, Hebrew and Spanish

Authors:  M. Elhadad, S. Miranda-Jiménez, Josef Steinberger, G. Giannakopoulos
Source:Elhadad, M., Miranda-Jiménez, S., Steinberger, J. and Giannakopoulos, G.: Multi-document multilingual summarization corpus preparation, Part 2: Czech, Hebrew and Spanish. In: Proceedings of the MultiLing 2013 Workshop on Multilingual Multi-document Summarization, pages 13-19, ACL. Sofia, Bulgaria, 2013.
Download: download Full text 
Publication

Multilingual Entity-Centered Sentiment Analysis Evaluated by Parallel Corpora

Authors:  Josef Steinberger, Polina Lenkova, Mijail Alexandrov Kabadjov, Ralf Steinberger, Erik var der Goot
Source:In: Proceedings of the 8th International Conference Recent Advances in Natural Language Processing, pages 770-775. Hissar, Bulgaria, 2011.
Download: download Full text 
Publication

Multilingual Media Monitoring and Text Analysis – Challenges for Highly Inflected Languages

Authors:  Ralf Steinberger, Maud Ehrmann, Julia Pajzs, Mohamed Ebrahim, Josef Steinberger, Marco Turchi
Source:Ralf Steinberger, Maud Ehrmann, Julia Pajzs, Mohamed Ebrahim, Josef Steinberger, Marco Turchi: Multilingual Media Monitoring and Text Analysis – Challenges for Highly Inflected Languages. In: Text, Speech and Dialogue (TSD'13), Lecture Notes in Computer Science 8082, pages 22-33, ISSN: 302-9743, DOI: 10.1007/978-3-642-40585-3_3, Springer. Pilsen, Czech Republic, 2013.
Download: download Full text 
Publication

Multilingual Statistical News Summarisation: Preliminary Experiments with English

Authors:  Mijail Alexandrov Kabadjov, Josef Steinberger, Bruno Pouliquen, Ralf Steinberger, Massimo Poesio
Source:In Proceedings of the workshop 'Intelligent Analysis and Processing of Web News Content' (WI-IAT'09). Milano, Italy, IEEE-CS Press, September 2009. ISBN 978-0-7695-3801-3.
View record in Web of Science®
Publication

Multilingual Statistical News Summarization

Authors:  Mijail Alexandrov Kabadjov, Josef Steinberger, Ralf Steinberger
Source:In: Thierry Poibeau, Horacio Saggion, Jakub Piskorski & Roman Yangarber (eds), Multi-source, Multilingual Information Extraction and Summarization, pages 229-252, ISSN: 2192-032X, DOI: 10.1007/978-3-642-28569-1_11, Springer. 2013.
ISSN:2192-032X
Download: download Full text 
Publication

Multilingual Summarisation and Sentiment Analysis

Authors:  Josef Steinberger
Source:Josef Steinberger: Multilingual Summarisation and Sentiment Analysis, Habilitation thesis. University of West Bohemia, April, 2013.
Download: download Full text [637 kB]
Publication

NewsGist: A Multilingual Statistical News Summarizer

Authors:  Mijail Alexandrov Kabadjov, Martin Atkinson, Josef Steinberger, Ralf Steinberger, Erik var der Goot
Source:In: Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science 6323, pages 591-594, ISSN: 302-9743, DOI:10.1007/978-3-642-15939-8_40, Springer. 2010.
ISSN:302-9743
Download: download Full text 
Publication

Relevance Ranking for Translated Texts

Authors:  Marco Turchi, Josef Steinberger, Lucia Specia
Source:In: Proceedings of 16th Annual Conference of the European Association for Machine Translation. Trento, Italy, 2012.
Download: download Full text 
Publication

SUTLER: Update Summarizer Based on Latent Topics

Authors:  Josef Steinberger, Karel Ježek
Source:In Proceedings of TAC'08, NIST, Gaithersburgh, United States, 2009.
Download: download Full text 
Publication

Searching and Summarizing in Multilingual Environment

Authors:  Michal Toman, Josef Steinberger, Karel Ježek
Source:In Proceedings of the 10th International Conference on Electronic Publishing, Bansko, Bulgaria, June 2006, pp. 257-265, FOI-Commerce, ISBN 954-16-0049-9.
Download: download Full text [197 kB]
Publication

Semi-automatic Acquisition of Lexical Resources and Grammars for Event Extraction in Bulgarian and Czech

Authors:  Hristo Tanev, Josef Steinberger
Source:Hristo Tanev and Josef Steinberger: Semi-automatic Acquisition of Lexical Resources and Grammars for Event Extraction in Bulgarian and Czech. In: Proceedings of the 4th Biennial International Workshop on Balto-Slavic Natural Language Processing, pages 110-118, ACL. Sofia, Bulgaria, 2013.
Download: download Full text 
Publication

Sentence Compression for the LSA-based Summarizer

Authors:  Josef Steinberger, Karel Ježek
Source:In Proceedings of the 7th International Conference on Information Systems Implementation and Modelling, Přerov, Czech Republic, April 2006, pp. 141-148, MARQ Ostrava, ISBN 80-86840-19-0.
Download: download Full text [152 kB]
Publication

Sentiment Analysis in Czech Social Media Using Supervised Machine Learning

Authors:  Ivan Habernal, Tomáš PtáÄek, Josef Steinberger
Source:Habernal, I., PtáÄek, T., Steinberger, J. (2013). Sentiment Analysis in Czech Social Media Using Supervised Machine Learning. Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, June, 2013, Atlanta, Georgia, USA, Association for Computational Linguistics.
Download: download Full text [256 kB]
Publication

Summarizing Opinions in Blog Threads

Authors:  Alexandra Balahur, Mijail Alexandrov Kabadjov, Josef Steinberger, Ralf Steinberger, Andrés Montoyo
Source:In: Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation (PACLIC), pages 606-613.Hong Kong, 2009.
Download: download Full text 
Publication

TAC 2011 multiling pilot overview

Authors:  G. Giannakopoulos, M. El-Haj, B.  Favre, M.  Litvak, Josef Steinberger, V.  Varma
Source:In: Proceedings of the Text Analysis Conference 2011, National Institute of Standards and Technology (NIST). Gaithersburg, USA, 2012.
Download: download Full text 
Publication

Task-Based Evaluation of Anaphora Resolution: The Case of Summarization

Authors:  Mijail Alexandrov Kabadjov, Massimo Poesio, Josef Steinberger
Source:In Proceedings of Recent Advances in Natural Language Processing Workshop â€Crossing Barriers in Text Summarization Researchâ€, Shoumen, Bulgaria, September 2005, pp. 18-25, Incoma Ltd., ISBN 954-90906-8-X.
Download: download Full text [150 kB]
Publication

Text Summarization and Singular Value Decomposition

Authors:  Josef Steinberger, Karel Ježek
Source:Proceedings the 3rd International Conference on Advances in Information Systems, Lecture Notes in Computer Science 2457, October 2004, pp. 245–254, Springer-Verlag Berlin Heidelberg, ISSN 0302-9743, ISBN 3-540-23478-0.
ISSN:0302-9743
View record in Web of Science®
Publication

Text Summarization via Latent Semantic Analysis and Anaphora Resolution

Authors:  Josef Steinberger
Source:Technical Report DCSE/TR-2005-01, Pilsen, Czech Republic, 2005.
Publication

Text Summarization within the LSA Framework

Authors:  Josef Steinberger
Source:PhD Thesis, University of West Bohemia in Pilsen, Czech Republic, January 2007.
Download: download Full text [994 kB]
Publication

Text Summarization: An Old Challenge and New Approaches

Authors:  Josef Steinberger, Karel Ježek
Source:Foundations of Computational Intelligence Vol.6, pages 127- 149, Data Mining Book Series, Springer 2009, ISSN 1860-949X, ISBN 978-3-642-01090-3
ISSN:1860-949X
Download: download Full text 
View record in Web of Science®
Publication

The UWB Summariser at Multiling-2013

Authors:  Josef Steinberger
Source:Steinberger, J.: The UWB Summariser at Multiling-2013. In: Proceedings of the MultiLing 2013 Workshop on Multilingual Multi-document Summarization, pages 50-54, ACL. Sofia, Bulgaria, 2013.
Download: download Full text 
Publication

Two Uses of Anaphora Resolution in Summarization

Authors:  Josef Steinberger, Massimo Poesio, Mijail Alexandrov Kabadjov, Karel Ježek
Source:In Special Issue of Information Processing & Management on Summarization, volume 43, issue 6, November 2007, Elsevier Ltd., pp. 1663-1680. ISSN 0306-4573.
ISSN:0306-4573
Download: download Full text 
View record in Web of Science®
Publication

Update Summarization Based on Latent Semantic Analysis

Authors:  Josef Steinberger, Karel Ježek
Source:In Proceedings of 12th International Conference, TSD 2009, Pilsen, Czech Republic, September 2009. LNAI 5729, Springer-Verlag Berlin Heidelberg New York, ISBN 978-3-642-04207-2, ISSN 0302-9743.
ISSN:0302-9743
Download: download Full text 
View record in Web of Science®
Publication

Update Summarization Based on Novel Topic Distribution

Authors:  Josef Steinberger, Karel Ježek
Source:In Proceedings of the 2009 ACM Symposium on Document Engineering, Munich, Germany, September 2009. Association for Computing Machinery, ISBN 978-1-60558-575-8.
Download: download Full text 
View record in Web of Science®
Publication

Using Latent Semantic Analysis in Text Summarization and Summary Evaluation

Authors:  Josef Steinberger, Karel Ježek
Source:In Proceedings of the 5th International Conference on Information Systems Implementation and Modelling, Rožnov p. Radhoštěm, Czech Republic, April 2004, pp. 93–100, MARQ Ostrava, ISBN 80-85988-99-2.
Download: download Full text [127 kB]
Publication

Using Parallel Corpora for Multilingual (Multi-Document) Summarisation Evaluation

Authors:  Marco Turchi, Josef Steinberger, Mijail Alexandrov Kabadjov, Ralf Steinberger
Source:In: Multilingual and Multimodal Information Access Evaluation, Springer Lecture Notes for Computer Science 6360/2010, pages 52-63, ISSN: 0302-9743, DOI:10.1007/978-3-642-15998-5_7, Springer. 2010.
ISSN:0302-9743
Download: download Full text 
View record in Web of Science®
Publication

WB-JRC-UT’s Participation in TAC 2009: Update Summarization and AESOP Tasks

Authors:  Josef Steinberger, Mijail Alexandrov Kabadjov, Bruno Pouliquen, Ralf Steinberger, Massimo Poesio
Source:In: Proceedings of the Text Analysis Conference 2009, National Institute of Standards and Technology. Gaithersburg, USA, 2010.
Download: download Full text 
Publication

Web Topic Summarization

Authors:  Josef Steinberger, Karel Ježek, Martin Sloup
Source:Proceedings of the 12th International Conference on Electronic Publishing, ISBN 978-0-7727-6315-0, pp 322-334, Toronto, Canada 2008
Download: download Full text [446 kB]
Publication

Wrapping up a Summary: from Representation to Generation

Authors:  Josef Steinberger, Marco Turchi, Mijail Alexandrov Kabadjov, Ralf Steinberger
Source:In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 382-386, ACL. Uppsala, Sweden, 2010.
Download: download Full text 

Projects:


Project

Multilingual Sentiment Analysis

Authors:  Josef Steinberger
Desc.:Sentiment analysis of news and social media in multiple languages.
Project

Automatic Text Summarisation

Authors:  Josef Steinberger, Karel Ježek, Michal Campr, Jiří Hynek
Desc.:Automatic text summarisation using various text mining methods, mainly Latent Semantic Analysis (LSA).
Project

Searching and Summarizing in Multilingual Enviroment

Authors:  Josef Steinberger, Karel Ježek, Michal Toman
Desc.:The project includes multilingual searching in text databases and an automatic summarization of retrieved texts. It was supported in part by the Ministry of Education of the Czech Republic under grant FRVS 1326/2005/G1.