Lecture Notes in Artificial Intelligence 7499 Subseries of Lecture Notes in Computer Science LNAISeriesEditors RandyGoebel UniversityofAlberta,Edmonton,Canada YuzuruTanaka HokkaidoUniversity,Sapporo,Japan WolfgangWahlster DFKIandSaarlandUniversity,Saarbrücken,Germany LNAIFoundingSeriesEditor JoergSiekmann DFKIandSaarlandUniversity,Saarbrücken,Germany Petr Sojka Aleš Horák Ivan Kopecˇek Karel Pala (Eds.) Text, Speech and Dialogue 15th International Conference, TSD 2012 Brno, Czech Republic, September 3-7, 2012 Proceedings 1 3 SeriesEditors RandyGoebel,UniversityofAlberta,Edmonton,Canada JörgSiekmann,UniversityofSaarland,Saarbrücken,Germany WolfgangWahlster,DFKIandUniversityofSaarland,Saarbrücken,Germany VolumeEditors PetrSojka MasarykUniversity FacultyofInformatics DepartmentofComputerGraphicsandDesign Botanická68a,60200,Brno,CzechRepublic E-mail:sojka@fi.muni.cz AlešHorák IvanKopecˇek KarelPala MasarykUniversity FacultyofInformatics DepartmentofInformationTechnologies Botanická68a,60200Brno,CzechRepublic E-mail:{hales,kopecek,pala}@fi.muni.cz ISSN0302-9743 e-ISSN1611-3349 ISBN978-3-642-32789-6 e-ISBN978-3-642-32790-2 DOI10.1007/978-3-642-32790-2 SpringerHeidelbergDordrechtLondonNewYork LibraryofCongressControlNumber:2012944853 CRSubjectClassification(1998):I.2,H.3-5,J.1,H.2,I.5,F.1 LNCSSublibrary:SL7–ArtificialIntelligence ©Springer-VerlagBerlinHeidelberg2012 Thisworkissubjecttocopyright.Allrightsarereserved,whetherthewholeorpartofthematerialis concerned,specificallytherightsoftranslation,reprinting,re-useofillustrations,recitation,broadcasting, reproductiononmicrofilmsorinanyotherway,andstorageindatabanks.Duplicationofthispublication orpartsthereofispermittedonlyundertheprovisionsoftheGermanCopyrightLawofSeptember9,1965, initscurrentversion,andpermissionforusemustalwaysbeobtainedfromSpringer.Violationsareliable toprosecutionundertheGermanCopyrightLaw. Theuseofgeneraldescriptivenames,registerednames,trademarks,etc.inthispublicationdoesnotimply, evenintheabsenceofaspecificstatement,thatsuchnamesareexemptfromtherelevantprotectivelaws andregulationsandthereforefreeforgeneraluse. Typesetting:Camera-readybyauthor,dataconversionbyScientificPublishingServices,Chennai,India Printedonacid-freepaper SpringerispartofSpringerScience+BusinessMedia(www.springer.com) Preface The annual Text, Speech and Dialogue Conference (TSD), which originated in 1998,is inthe middle ofits seconddecade.So farmore than1,000authorsfrom 45 countries have contributed to the proceedings. TSD constitutes a recognized platform for the presentation and discussion of state-of-the-art technology and recent achievements in the field of natural language processing. It has become an interdisciplinary forum, interweaving the themes of speech technology and language processing. The conference attracts researchers not only from Central and Eastern Europe but also from other parts of the world. Indeed, one of its goalshas alwaysbeen to bring togetherNLP researcherswith differentinterests from different parts of the worldand to promote their mutual cooperation.One of the ambitions of the conference is, as its title says, not only to deal with dialogue systems as such, but also to contribute to improving dialogue between researchersinthe twoareasofNLP,i.e.,betweentextandspeechpeople.Inour view, the TSD Conference was successful in this respect in 2012 again. This volume contains the proceedings of the 15th TSD Conference, held in Brno,CzechRepublic,inSeptember2012.Inthereviewprocess,82paperswere accepted out of 173 submitted, an acceptance rate of 47%. We would like to thank all the authors for the efforts they put into their submissions and the members of the Program Committee and reviewers who did a wonderful job in helping us to select the most appropriate papers. We are also grateful to the invited speakers for their contributions. Their talks provide insightintoimportantcurrentissues,applications,andtechniquesrelatedtothe conference topics. LastyeartheworkshoponNaturalLanguageProcessingofBalticandSlavonic LanguagestookplaceintheframeoftheTSDConference.Thisyearaworkshop on Hybrid Machine Translation was organized together with the conference. In partit wasrelatedto the EUprojectPRESEMT(FP7/2007-2013,ICT 248307) in which organizers participate. Special thanks are due to the members of Local Organizing Committee for their tireless effort in organizing the conference. The TEXpertise of Petr Sojka resulted in the production of the volume that you are holding in your hands. We hope that the readers will benefit from the results of this event and disseminate the ideas of the TSD Conference all over the world. Enjoy the proceedings! July 2012 Aleˇs Hor´ak Ivan Kopeˇcek Karel Pala Petr Sojka Organization TSD2012wasorganizedbytheFacultyofInformatics,MasarykUniversity,inco- operation with the Faculty of Applied Sciences, University of West Bohemia in Plzenˇ.Theconferencewebpageislocatedathttp://www.tsdconference.org/tsd2012/ Program Committee Hermansky, Hynek (USA), N¨oth, Elmar (Germany) General Chair Oliva, Karel (Czech Republic) Agirre, Eneko (Spain) Pala, Karel (Czech Republic) Cˇernocky´, Jan (Czech Republic) Pavesi´c,Nikola (Slovenia) Ferencz, Attila (Romania) Petkeviˇc, Vladim´ır (Czech Republic) Fiˇser, Darja (Slovenia) Pianesi, Fabio (Italy) Garab´ık,Radovan (Slovakia) Piasecki, Maciej (Poland) Gelbukh, Alexander (Mexico) Przepiorkowski,Adam (Poland) Guthrie, Louise, (UK) Psutka, Josef (Czech Republic) Hajiˇc, Jan (Czech Republic) Pustejovsky, James (USA) Hajiˇcov´a,Eva (Czech Republic) Rothkrantz, Leon (The Netherlands) Hanks, Patrick (UK) Rusko, Milan (Slovakia) Hitzenberger, Ludwig (Germany) Skrelin, Pavel(Russia) Hlava´ˇcov´a,Jaroslava Smrˇz, Pavel(Czech Republic) (Czech Republic) Sojka, Petr (Czech Republic) Hora´k, Aleˇs (Czech Republic) Steidl, Stefan (Germany) Hovy, Eduard (USA) Stemmer, Georg (Germany) Kopeˇcek, Ivan (Czech Republic) Tadi´c, Marko (Croatia) Krauwer,Steven (The Netherlands) Varadi, Tamas (Hungary) Kunzmann, Siegfried (Germany) Vetulani, Zygmunt (Poland) Loukachevitch, Natalija (Russia) Vintsiuk, Taras (Ukraine) Matouˇsek, V´aclav (Czech Republic) Wiggers, Pascal(The Netherlands) McCarthy, Diana (UK) Wilks, Yorick (UK) Ney, Hermann (Germany) Zakharov,Victor (Russia) Referees Alegria, In˜aki Diaz de Ilarraza,Arantza Arregi Uriarte, Olatz Evdokimova, Vera Baisa, V´ıt Evgrafova,Karina Benˇuˇs, Sˇtefan Fellbaum, Christiane Broda, Bartosz Gr´ezl, Frantiˇsek Cernˇak, Miloˇs Guthrie, Joe VIII Organization Hannemann, Mirko Mra´kova´,Eva Hlava´ˇckov´a,Dana Nedoluzhko, Anna Holub, Martin Nˇemˇc´ık,Va´clav H´eja, Eniko˝ Nevˇeˇrilova´,Zuzana Kamshilova, Olga Oravecz, Csaba Karafia´t, Martin Otegi, Arantxa Khokhlova, Maria Peterek, Nino Kocharov,Daniil Popel, Martin Lopez de Lacalle, Oier Radziszewski, Adam Marcin´czuk, Michal(cid:3) Rigau Claramunt, German Mareˇcek,David R˚uˇziˇcka, Michal Materna, Jiˇr´ı Sass, B´alint Matˇejka, Pavel Sazhok, Mykola Maziarz, Marek Stemmer, Georg Miheliˇc, France Sz¨oke, Igor Miha´ltz, Ma´rton Vesely´, Karel Mikolov, Toma´ˇs Wardyn´ski, Adam Mitrofanova, Olga Organizing Committee Dana Hlava´ˇckov´a(Administrative Contact), Aleˇs Hor´ak (Co-chairs), Dana Koma´rkov´a(Secretary), Ivan Kopeˇcek, Karel Pala (Co-chair), Adam Rambousek (Web System), PavelRychly´, Petr Sojka (Proceedings) Sponsors and Support The TSD conference is regularly supported by International Speech Communi- cation Association (ISCA). We would like to express our thanks to the Lexical Computing Ltd., for their kind sponsoring contribution to TSD 2012. Table of Contents Part I: Invited Papers Getting to Know Your Corpus..................................... 3 Adam Kilgarriff Coreference Resolution: To What Extent Does It Help NLP Applications?.................................................... 16 Ruslan Mitkov, Richard Evans, Constantin Or˘asan, Iustin Dornescu, and Miguel Rios Part II: Text Semantic Similarity Functions in Word Sense Disambiguation.......... 31 L(cid:3) ukasz Kobylin´ski and Mateusz Kope´c Opinion Mining on a German Corpus of a Media Response Analysis.... 39 Thomas Scholz, Stefan Conrad, and Lutz Hillekamps The Soundex Phonetic Algorithm Revisited for SMS Text Representation .................................................. 47 David Pinto, Darnes Vilarin˜o, Yuridiana Alema´n, Helena G´omez, Nahun Loya, and H´ector Jim´enez-Salazar Sentence Modality Assignment in the Prague Dependency Treebank.... 56 Magda Sˇevˇc´ıkova´ and Jiˇr´ı M´ırovsk´y Literacy Demands and Information to Cancer Patients................ 64 Dimitrios Kokkinakis, Markus Forsberg,SofieJohansson Kokkinakis, Frida Smith, and Joakim O¨hlen Expanding Opinion Attribute Lexicons ............................. 72 Aleksander Wawer and Konrad Go(cid:3)luchowski Taggers Gonna Tag: An Argument against Evaluating Disambiguation Capacities of Morphosyntactic Taggers.............................. 81 Adam Radziszewski and Szymon Acedan´ski An Ambiguity Aware Treebank Search Tool ......................... 88 Marcin Wolin´ski and Andrzej Zaborowski X Table of Contents A New Annotation Tool for Aligned Bilingual Corpora................ 95 Georgios Petasis and Mara Tsoumari Optimizing Sentence Boundary Detection for Croatian................ 105 Frane Sˇari´c, Jan Sˇnajder, and Bojana Dalbelo Baˇsi´c Mining the Web for Idiomatic Expressions Using Metalinguistic Markers ........................................................ 112 Filip Gralin´ski Using Tree Transducers for Detecting Errors in a Treebank of Polish ... 119 Katarzyna Krasnowska, Witold Kiera´s, Marcin Wolin´ski, and Adam Przepio´rkowski Combining Manual and Automatic Annotation of a Learner Corpus .... 127 Toma´ˇs Jel´ınek, Barbora Sˇtindlov´a, Alexandr Rosen, and Jirka Hana A Manually Annotated Corpus of PharmaceuticalPatents............. 135 Ma´rton Kiss, A´goston Nagy, Veronika Vincze, Attila Alm´asi, Zolt´an Alexin, and Ja´nos Csirik Large-Scale Experiments with NP Chunking of Polish ................ 143 Adam Radziszewski and Adam Pawlaczek Mapping a Lexical Semantic Resource to a Common Framework of Computational Lexicons .......................................... 150 Milena Slavcheva The Rule-Based Approach to Czech Grammaticalized Alternations ..... 158 V´aclava Kettnerova´, Mark´eta Lopatkov´a, and Zdenˇka Ureˇsov´a Semi-supervised Acquisition of Croatian Sentiment Lexicon ........... 166 Goran Glavaˇs, Jan Sˇnajder, and Bojana Dalbelo Baˇsi´c Towards a Constraint Grammar Based Morphological Tagger for Croatian........................................................ 174 Hrvoje Peradin and Jan Sˇnajder A Type-Theoretical Wide-Coverage Computational Grammar for Swedish......................................................... 183 Malin Ahlberg and Ramona Enache Application of Lemmatization and Summarization Methods in Topic Identification Module for Large Scale Language Modeling Data Filtering ........................................................ 191 Lucie Skorkovska´ Experiments and Results with Diacritics Restoration in Romanian ..... 199 Cristian Grozea Table of Contents XI Supervised Distributional Semantic Relatedness...................... 207 Alistair Kennedy and Stan Szpakowicz PSI-Toolkit: How to Turn a Linguist into a Computational Linguist .... 215 Krzysztof Jassem Heterogeneous Named Entity Similarity Function .................... 223 Jan Kocon´ and Maciej Piasecki Joint Part-of-Speech Tagging and Named Entity Recognition Using Factor Graphs................................................... 232 Gyo¨rgy Mo´ra and Veronika Vincze Assigning Deep Lexical Types ..................................... 240 Jo˜ao Silva and Ant´onio Branco SBFC: An Efficient Feature Frequency-Based Approach to Tackle Cross-LingualWord Sense Disambiguation .......................... 248 Dieter Mourisse, Els Lefever, Nele Verbiest, Yvan Saeys, Martine De Cock, and Chris Cornelis Dependency Relations Labeller for Czech ........................... 256 Rudolf Rosa and David Mareˇcek Preliminary Study on Automatic Induction of Rules for Recognition of Semantic Relations between Proper Names in Polish Texts ............ 264 Michal(cid:3) Marcin´czuk and Marcin Ptak Actionable Clause Detection from Non-imperative Sentences in Howto Instructions: A Step for Actionable Information Extraction............ 272 Jihee Ryu, Yuchul Jung, and Sung-Hyon Myaeng Authorship Attribution: Comparison of Single-Layer and Double-Layer Machine Learning................................................ 282 Jan Rygl and Aleˇs Hora´k Key Phrase Extraction of Lightly Filtered Broadcast News ............ 290 Lu´ıs Marujo, Ricardo Ribeiro, David Martins de Matos, Jo˜ao P. Neto, Anatole Gershman, and Jaime Carbonell Using a Double Clustering Approach to Build Extractive Multi-document Summaries ....................................... 298 Sara Botelho Silveira and Ant´onio Branco A Comparative Study of the Impact of Statistical and Semantic Features in the Framework of Extractive Text Summarization ......... 306 Tatiana Vodolazova, Elena Lloret, Rafael Mun˜oz, and Manuel Palomar XII Table of Contents Using Dependency-Based Annotations for Authorship Identification .... 314 Charles Hollingsworth A Space-Efficient Phrase Table Implementation Using Minimal Perfect Hash Functions .................................................. 320 Marcin Junczys-Dowmunt Common Sense Inference Using Verb Valency Frames................. 328 Zuzana Nevˇeˇrilova´ and Marek Gra´c A Genetic Programming Experiment in Natural Language Grammar Engineering ..................................................... 336 Marcin Junczys-Dowmunt User Modeling for Language Learning in Facebook ................... 345 Maria Virvou, Christos Troussas, Jaime Caro, and Kurt Junshean Espinosa Detection of Semantic Compositionality Using Semantic Spaces........ 353 Lubom´ır Krˇcma´ˇr, Karel Jeˇzek, and Massimo Poesio User Adaptation in a Hybrid MT System: Feeding User Corrections into Synchronous Grammars and System Dictionaries................. 362 Susanne Preuß, Hajo Keffer, Paul Schmidt, Georgios Goumas, Athanasia Asiki, and Ioannis Konstantinou Using Cognates to Improve Lexical Alignment Systems ............... 370 Mirabela Navlea and Amalia Todirascu Disambiguating Word Translations with Target Language Models ...... 378 Andr´e Lynum, Erwin Marsi, Lars Bungum, and Bjo¨rn Gamba¨ck English-Vietnamese Machine Translation of Proper Names: Error Analysis and Some Proposed Solutions ............................. 386 Thi Thanh Thao Phan and Izabella Thomas Improved Phrase Translation Modeling Using MAP Adaptation........ 394 A. Ryan Aminzadeh, Jennifer Drexler, Timothy Anderson, and Wade Shen Part III: Speech A Romanian Language Corpus for a Commercial Text-To-Speech Application ..................................................... 405 Mihai Alexandru Ordean, Andrei S¸aupe, Mihaela Ordean, Gheorghe Cosmin Silaghi, and Corina Giurgea