Slovenian Language Technologies Society

Information Society - IS 2006

Fifth Slovenian and First International
Language Technologies Conference

IS-LTC 2006

October 9 - 10, 2006
Ljubljana
Slovenia

This biennial conference was organised by the Slovenian Language Technologies Society and held in the scope of the Information Society - IS 2006 which took place October 9 - 13, 2006 at the Jožef Stefan Institute in Ljubljana, Slovenia. This event was the fifth in the series of Slovenian Language Technologies Conferences ('98, '00, '02, '04), for the first time organised as an international conference, with an international programme committee. The official languages of the conference were English and Slovene. The conference was organised in two tracks, one for contributions in English, and the other for those in Slovenian. The accepted papers were published in printed proceedings, as well as on-line.

New!
On-line Proceedings Invited Talks Schedule of Talks Programme Committee Organising Committee

Invited talks

Nick Campbell
Spoken Language Communication Group
National Institute of Information and Communication Technology, Japonska

Speech Synthesis and Discourse Information

Abstract
This paper describes some recent work towards a conversational speech synthesis system for use in interactive dialogues between a human and an information system, robot, or speech translation device. The paper describes several response-type utterances that are currently very difficult to implement using traditional speech synthesis methods, and shows how these non-verbal speech sounds function to provide feedback and status-updates in an interactive discourse. The talk will be illustrated with examples of such utterances, which include laughter and grunts as well as common phrases and idiom, showing how their variety can reveal several types of information about the speaker-(i.e., listener) states. The paper proposes a model of information exchange (through speech) whereby this feedback from the listener allows the speaker to efficiently deliver content and to be assured of successful information transmission.

Steven Krauwer
Coordinator of ELSNET (European Network of Excellence in Human Language Technologies)
Utrecht University, Netherlands

Strengthening the smaller languages in Europe

Abstract
The problem we want to address is that - even if the complexity of a language is independent of the number of speakers - industrial developers of language and speech technology (and, unfortunately, hence the EU R&D programmes) focus their efforts on the major languages, because of their economic potential. This is something we cannot change, but in our talk we will discuss what the smaller language communities can do to create optimal conditions for the development of their own language and speech technologies.

Program of the Conference

Monday, October 9, 2006

8:30 - 9:00	registration
9:00 - 11:00	opening of the conference invited lectures: Steven Krauwer: Strengthening the Smaller Languages in Europe Nick Campbell: Speech Synthesis and Discourse Information
11:00 - 11:30	coffee break
11:30 - 13:30	Korbinian Riedhammer, Tino Haderlein, Maria Schuster, Frank Rosanowski, Elmar Nöth: Automatic Evaluation of Tracheoesophageal Telephone Speech Andras Banhalmi, Denes Paczolay, Laszlo Toth, Andras Kocsor: First Results of a Hungarian Medical Dictation Project Margus Treumuth, Tanel Alumäe, Einar Meister: A Natural Language Interface to a Theater Information Database Andreas Maier, Elmar Nöth, Emeka Nkenke, Maria Schuster: Automatic Assessment of Children's Speech with Cleft Lip and Palate Martin Karafiat, Frantisek Grezl, Petr Schwarz, Lukas Burget, Jan Cernocky: Robust heteroscedastic linear discriminant analysis and LCRC posterior features in large vocabulary continuous speech recognition Nikša Jakovljević, Dragiša Mišković, Milan Sečujski, Darko Pekar: Vocal Tract Normalization Based on Formant Positions Jerneja Žganec Gros, Varja Cvetko-Orešnik, Primož Jakopin: SI-PRON: a Comprehensive Pronunciation Lexicon for Slovenian Darinka Verdonik: Pragmatically annotated corpora in speech-to-speech translation
13:30 - 14:30	lunch break
14:30 - 16:00	Atanas Chanev: Studying the Learning Curves of a Statistical Dependency Parser for Four Languages Simon Krek, Adam Kilgarriff: Slovene Word Sketches Matthias Richter, Uwe Quasthoff, Erla Hallsteinsdóttir, Chris Biemann: Exploiting the Leipzig Corpora Collection Michael Pucher, Yan Huang, Ozgur Cetin: Optimization of Latent Semantic Analysis based Language Model Interpolation for Meeting Recognition Isabel Segura Bedmar, Jose L. Martinez-Fernandez, P. Martinez: Including deeper semantic information in the Lexical Markup Framework: a proposal Jori Mur: Increasing the coverage of answer extraction by applying anaphora resolution
16:00 - 16:30	coffee break
16:30 - 18:30	Simon Dobrišek, Boštjan Vesnicer, Jerneja Žganec Gros, France Mihelič: Uporaba kanoničnega govornega akustičnega modela za prilagajanje prostora govornih akustičnih značilk Špela Arhar, Miro Romih: Klepec: programirani sogovornik za slovenščino Andrej Žgank, Tomaž Rotovnik, Mirjam Sepesy Maučec, Zdravko Kačič: Osnovna zgradba razpoznavalnika slovenskega tekočega govora UMB Broadcast News Melita Hajdinjak, France Mihelič: Rezultati vrednotenja dveh sistemov Čarovnik iz Oza Melita Hajdinjak, France Mihelič: Vrednotenje govornih vmesnikov z ogrodjem PARADISE Andrej Žgank, Tomaž Rotovnik, Matej Grašič, Marko Kos, Damjan Vlaj, Zdravko Kačič: Slovenska govorna in tekstovna baza parlamentarnih razprav za avtomatsko razpoznavanje govora Jasna Belc, Miran Željko: Načelo večjezičnosti ali večjezični korpus iz manjše množice dvojezičnih Jana Zemljarič Miklavčič: Korpus govorjene slovenščine
18:30 - ...	welcome reception

Tuesday, October 10, 2006

9:00 - 11:00	Agnes Pisanski Peterlin: Iskanje pragmatičnih enot v neoznačenem korpusu: primer kažipotov Mojca Stritar: Oblikovanje korpusa usvajanja slovenščine kot tujega jezika Peter Holozan: Dodatne dvoumnosti zaradi popustljivosti analizatorja pri analizi slovenskih stavkov Mihael Arčan, Špela Vintar: Avtomatično prepoznavanje lastnih imen Katarina Puc, Tomaž Erjavec: Uporaba korpusa pri urejanju spletnega terminološkega slovarja Tomaž Erjavec, Nina Ledinek: Slovenska odvisnostna drevesnica: prvi rezultati Tomaž Erjavec, Bence Sárossy: Oblikoslovno označevanje slovenskega jezika: primer korpusa SVEZ-IJS
11:00 - 11:30	coffee break
11:30 - 13:30	Ralf Engel: SPIN: A Semantic Parser for Spoken Dialog Systems Aneta Ivanovska, Katerina Zdravkova, Tomaž Erjavec, Sašo Džeroski: Learning rules for morphological analysis and synthesis of Macedonian nouns, adjectives and verbs Antoine Doucet, Helena Ahonen-Myka: Fast extraction of discontiguous sequences in text: a new approach based on maximal frequent sequences Cvetana Krstev, Duško Vitas: Finite State Transducers for Recognition and Generation of Compound Words Sanja Seljan: The Role of the Lexicon in Lexical Functional Grammar - Example of Croatian Daniel Sonntag: Towards Combining Finite State, Ontologies, and Data Driven Approaches to Dialogue Management for Multimodal Question Answering Špela Vintar, Darja Fišer, Ljupčo Todorovski: Towards clustering-based word sense discrimination
13:30 - 14:45	lunch break
14:45 - 16:00	Milan Sečujski, Vlado Delić: A Software Tool for Semi-Automatic Part-of-Speech Tagging and Sentence Accentuation in Serbian Language Jerneja Žganec Gros, Vlado Delić, Darko Pekar, Milan Sečujski, Aleš Mihelič: The iTEMA e-mail reader Jerneja Žganec Gros, Stanislav Gruden, France Mihelič, Tomaž Erjavec, Špela Vintar, Peter Holozan, Aleš Mihelič, Simon Dobrišek, Janez Žibert, Nataša Logar, Tomo Korošec: The VoiceTRAN Speech Translation Demonstrator Anton Batliner, Stefan Steidl, Björn Schuller, Dino Seppi, Kornel Laskowski, Thurid Vogt, Laurence Devillers, Laurence Vidrascu, Noam Amir, Loic Kessous, Vered Aharonson: Combining Efforts for Improving Automatic Classification of Emotional User States Anton Batliner, Felix Burkhardt, Markus van Ballegooy, Elmar Nöth: A Taxonomy of Applications that Utilize Emotional Awareness
16:00 - 16:30	coffee break
16:30 - 18:00	Sanda Martinčić - Ipšić, Ivo Ipšić: Context-Dependent Acoustic Modelling of Croatian Speech Vlado Delić, Milan Sečujski, Darko Pekar, Nikša Jakovljević, Dragiša Mišković: A Review of AlfaNum Speech Technologies for Serbian, Croatian and Macedonian Rusko Milan, Trnka Marian, Darjaa Sakhia: Slovak TTS - From Rule Based To Unit Selection Wesley Mattheyses, Lukas Latacz, Yuk On Kong, Werner Verhelst: A Flemish Voice for the Nextens Text-To-Speech System Jan Macek, Julie Carson-Berndsen: Articulatory Manner Features Recognition with Linear and Polynomial Kernels Grega Milharčič, Janez Žibert, France Mihelič: Statistical Language Modeling of SiBN Broadcast News Text Corpus
19:30 - 21:30	conference dinner

Programme Committee

Jan Cernocký, Faculty of Information Technology, Brno Technical University (Czech Republic)
Christoph Draxler, Institute of Phonetics and Speech Communication, Ludwig-Maximilians-Universitaet Munich (Germany)
Tomaž Erjavec (chair), Dept. of Knowledge Technologies, Jožef Stefan Institute (Slovenia)
Sadaoki Furui, Graduate School of Information Science and Engineering, Tokyo Institute of Technology (Japan)
Carmen Garcia-Mateo, ETSI Telecomunicacion, Vigo University (Spain)
Vojko Gorjanc, Faculty of Arts, University of Ljubljana (Slovenia)
Nancy Ide, Department of Computer Science, Vassar College (USA)
Bojan Imperl, Iskratel Ltd (Slovenia)
Ivo Ipsić, Faculty of Engineering, University of Rijeka (Croatia)
Zdravko Kačič, Faculty of Electrical Engineering and Computer Science, University of Maribor (Slovenia)
Adam Kilgarriff, Lexical Computing Ltd (UK)
Jin-Dong Kim, Tsujii Laboratory, University of Tokyo (Japan)
Cvetana Krstev, Arts Faculty, University of Belgrade (Serbia and Montenegro)
Siegfried Kunzmann, EMEA voice technology Development, IBM (Germany)
Gianni Lazzari, Interactive Sensory Systems Division, ITC-irst (Italy)
Bente Maegaard, Centre for Language Technology, University of Copenhagen (Denmark)
Jean-Pierre Martens, Department of Electronics and Information Systems, University of Gent (Belgium)
Dunja Mladenić, Dept. of Knowledge Technologies, Jožef Stefan Institute (Slovenia)
France Mihelič, Faculty of Electrical Engineering, University of Ljubljana (Slovenia)
João Paulo Neto, Spoken Language Laboratory, INESC-ID (Portugal)
Elmar Nöth, Technical Faculty, Friedrich-Alexander University Erlangen-Nuremberg (Germany)
Karel Pala, Faculty of Informatics, Masaryk University (Czech Republic)
Marko Stabej, Faculty of Arts, University of Ljubljana (Slovenia)
Tanja Schultz, Carnegie Mellon University (USA)
Tomaž Šef, Dept. for Intelligent Systems, Jožef Stefan Institute (Slovenia)
Rastislav Šuštaršič, Faculty of Arts, University of Ljubljana (Slovenia)
Marko Tadić, Department of linguistics, University of Zagreb (Croatia)
Jörg Tiedemann, Alfa-Informatica, Rijksuniversiteit Groningen (Netherlands)
Dan Tufiş, Research Institute for Artificial Intelligence, Romanian Academy (Romania)
Tamás Váradi, Linguistics Institute, Hungarian Academy of Sciences (Hungary)
Špela Vintar, Faculty of Arts, University of Ljubljana (Slovenia)
Andreja Žele, Fran Ramovš Institute of the Slovenian Language, ZRC-SAZU (Slovenia)
Jerneja Žganec Gros (chair), Alpineon Ltd (Slovenia)