multilingual information processing department

Violeta Seretan

Contact information:
ISSCO/TIM/ETI,
University of Geneva
40 bd. du Pont-d'Arve
CH-1211 Geneva 4
Switzerland
Tel: +41 22 379 8683
Office number: 6336
Violeta's email

*** News *** Multi-word Units in Machine Translation and Translation Technology, Workshop at MT Summit XIV, Nice, France (September 3, 2013) *** News ***

Background and Research Interests

I am a Senior Researcher at the Faculty of Translation and Interpreting, University of Geneva. I joined TIM/ISSCO in September 2011 to carry out research on statistical machine translation in the framework of the ACCEPT European project.

I have previously been a Senior Researcher at LATL in the Department of Linguistics, University of Geneva (2008-2010), then a Visiting Researcher at ILCC, School of Informatics, University of Edinburgh (2010-2011). I have received my PhD in Computational Linguistics from the University of Geneva in June, 2008. My PhD thesis "Collocation Extraction Based on Syntactic Parsing" (supervisor: Eric Wehrli) has been awarded the University of Geneva Latsis 2010 Prize and has been at the root of a monograph published in 2011 by Springer. [Full list of publications]

I have been working on Computational Linguistics ever since I was an undergraduate student in Computer Science at the University of Iasi, Romania, and a member of the NLP Group led by Dan Cristea. My research has been focused on topics related to language analysis, computational lexicography, and, more recently, to machine translation and language generation:

Teaching Activities

I teach the following courses:

Recent publications (past 5 years)

  • Seretan, Violeta and Eric Wehrli (2013). Syntactic concordancing and multi-word expression detection. Int. J. Data Mining, Modelling and Management, Vol. 5, No. 2, pp.158–181.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta and Eric Wehrli (to appear). Context-sensitive look-up in electronic dictionaries. In Rufus H. Gouws, Ulrich Heid, Wolfgang Schweickard, Herbert Ernst Wiegand (editors) Dictionaries. An international encyclopedia of lexicography. Supplementary volume: Recent developments with special focus on computational lexicography, Handbooks of Linguistics and Communications Science. Walter de Gruyter, Berlin/New York.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta (2012). A multilingual integrated framework for processing lexical collocations. In Adam Przepiorkowski et al. (eds.) Computational Linguistics – Applications, Studies in Computational Intelligence 458, pages 87–108. Springer. DOI: 10.1007/978-3-642-34399-5-5.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta (2012). Acquisition of Syntactic Simplification Rules for French. In Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12), Istanbul, Turkey.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta (2011). A Collocation-Driven Approach to Text Summarization. In Actes de la 18e conférence sur le Traitement Automatique des Langues Naturelles, pages 9–14, Montpellier, France.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta and Eric Wehrli (2011). FipsCoView: On-line Visualisation of Collocations Extracted from Multilingual Parallel Corpora. In Proceedings of the Workshop on Multiword Expressions: from Parsing and Generation to the Real World , pages 125–127, Portland, Oregon, USA.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta (2011). Syntax-Based Collocation Extraction. Springer (Text, Speech and Language Technology, volume 44). ISBN: 978-94-007-0133-5.

[bib] [Amazon page/reviews]
  • Wehrli, Eric, Violeta Seretan, and Luka Nerima (2010). Sentence analysis and collocation identification. In Proceedings of the Workshop on Multiword Expressions: from Theory to Applications (MWE 2010), pages 27–35, Beijing, China.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta and Eric Wehrli (2010). Tools for syntactic concordancing. In Proceedings of the International Multiconference on Computer Science and Information Technology, pages 493–500, Wisła, Poland.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta and Eric Wehrli (2010). Extending a multilingual symbolic parser to Romanian. In Dan Tufis and Corina Forascu (eds.): Multilinguality and Interoperability in Language Processing with Emphasis on Romanian, Romanian Academy Publishing House.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta, Eric Wehrli, Luka Nerima, and Gabriela Soare (2010). FipsRomanian: towards a Romanian version of the Fips syntactic parser. In Proceedings of the Seventh Conference on International Language Resources and Evaluation (LREC'10), Valletta, Malta.
    [html abstract] [pdf] [bib] [poster]
  • Luka Nerima, Eric Wehrli, and Violeta Seretan (2010). A recursive treatment of collocations. In Proceedings of the Seventh Conference on International Language Resources and Evaluation (LREC'10), Valletta, Malta.
    [html abstract] [pdf] [bib]
  • Wehrli, Eric, Luka Nerima, Violeta Seretan, and Yves Scherrer (2009). On-line and off-line translation aids for non-native readers. In Proceedings of the International Multiconference on Computer Science and Information Technology, pages 299–303, Mrągowo, Poland.
    [html abstract] [pdf] [bib]
  • Seretan, Violeta (2009). Extraction de collocations et leurs équivalents de traduction à partir de corpus parallèles ('Extracting collocations and translation equivalents from parallel corpora'). TAL, 50(1):305–332. In French.
    [html abstract] [pdf] [bib] [data: VO, AN, NPN]
  • Seretan, Violeta (2009). An integrated environment for extracting and translating collocations. In Proceedings of the Fifth Corpus Linguistics Conference, Liverpool, U.K.
    [html abstract] [pdf] [bib]
  • Wehrli, Eric, Violeta Seretan, Luka Nerima, and Lorenza Russo (2009). Collocations in a rule-based MT system: A case study evaluation of their translation adequacy. In Proceedings of the 13th Annual Meeting of the European Association for Machine Translation, pages 128–135, Barcelona, Spain.
    [html abstract] [pdf] [bib]
  • Michou, Athina and Violeta Seretan (2009). A tool for multi-word expression extraction in Modern Greek using syntactic parsing. In Proceedings of the Demonstrations Session at EACL 2009, pages 45–48, Athens, Greece.
    [html abstract] [pdf] [bib]
Full list of publications

Reviewing

RANLP 2013, *SEM-2012, LREC 2012, ACL 2012, EACL 2012, CIJC 2012, ConsILR 2011, CLA'11, RANLP 2011, MWE 2011, ACL/HLT 2011, CLA'10, ConsILR 2010, MWE 2010, COLING 2010, ACL 2010, LREC 2010, PROMISE 2010, MWE 2009, ConsILR 2009, ConsILR 2008, MWE 2008, ConsILR 2007, ACL07-MWE, EUROLAN 2007 Doctoral Consortium, RANLP-2007, AMML (W6@RANLP 2007), MWE 2006, ROMAND 2006

Revue de linguistique et de didactique des langues (2013), ACM TSLP Special Issue on MWEs (2012), Journal of the American Society for Information Science and Technology (2012), Natural Language Engineering (2011, 2008), Transactions on Intelligent Systems and Technology (2010), Language Resources and Evaluation (2008), Computational Linguistics (December 2007, Vol. 33, No. 4)

Conference organisation