International Conference RANLP-2003 - Programme September 10th (Wednesday)

8.45-9.00 Opening (BULGARIA hall)
9.00-10.00 Inderjeet Mani: New Developments in Extracting Temporal Information (invited talk)
Lexical knowledge acquisition from corpora

10.00-10.30:Identifying Lexical Paraphrases From a Single Corpus: A Case Study for Verbs, Oren Glickman and Ido Dagan

10.30-11.00: Extraction of Multi-Word Collocations Using Syntactic Bigram Composition, Violeta Seretan, Luka Nerima and Eric Wehrli


10.00-10.30: A Larger-first Approach to Partial Parsing, Sebastian van Delden and Fernando Gomez

10.30-11.00: Structured Parameter Estimation for LFG-DOP using Backoff, Mary Hearne and Khalil Sima'an

11.00-11.30 Coffee Break

Information extraction, text summarisation, evaluation issues in tagging/parsing

11.30-11.55: Automatic Evaluation of Robustness and Degradation in Tagging and Parsing, Johnny Bigert, Ola Knutsson and Jonas Sjobergh

11.55-12.20: Combining Heterogeneous Knowledge Sources in E-mail Summarization, Laura Alonso, Bernardino Casas, Irene Castellon, Savador Climent, Lluis Padro

12.20-12.45: Cross-lingual Information Extraction from Web pages: the Use of a General-purpose Text Engineering Platform, Georgios Petasis, Vangelis Karkaletsis and Constantine D. Spyropoulos


11.30-11.55: Consistent Discourse Segmentation for Rhetorical Representation Purposes, Naila. K. Mimouni

11.55-12.20: An Authoring Framework for Dialogue Forms Development in Conversational Applications, Lazaros C. Polymenakos and John K. Soldatos

12.20-12.45: A Task and Dialogue Model Independent Dialogue Manager, Marcela Charfuelan and Niels Ole Bernsen

12.45-14.30 Lunch
14.30-15.30 Branimir Boguraev: Annotations-based finite-state processing in a large scale NLP architecture (invited talk)

Tagging / Parsing

15.30-16.00: Why Build Another Part-of-Speech Tagger? A Minimalist Approach, Leonid Peshkin and Virginia Savova

16.00-16.30: Parsing Without Grammar - Using Complete Trees Instead, Sandra Kubler

Information / Event Extraction

15.30-16.00: Domain-Independent Detection, Extraction, and Labeling of Atomic Events, Elena Filatova and Vasileios Hatzivassiloglou

16.00-16.30: Semantically driven approach for scenario recognition in IE system FRET, Svetla Boytcheva, Milena Yankova and Albena Strupchanska

16.30-17.00 Coffee Break

Lexical semantics

17.00-17.30: Combining Independent Modules to Solve Multiple-choice Synonym and Analogy Problems, Peter D. Turney, Michael L. Littman, Jeffrey Bigham, and Victor Shnayder

17.30-18.00: Roget's Thesaurus and Semantic Similarity, Mario Jarmasz and Stan Szpakowicz


17.00-17.30: A constraint-based bottom-up counterpart to DCG, Henning Christiansen

20.00 Conference Reception, including folk programme (2045-2145) and dances after 2200


International Conference RANLP-2003 - Programme September 11th (Thursday)

9.00-10.00 Hans Uszkoreit (invited talk)

Document similarity

10.00-10.30: Towards Deeper Understanding of LSA Performance, Preslav Nakov, Elena Valchanova and Galia Angelova

10.30-11.00: Automatic Identification of Document Translations in Large Multilingual Document Collections, Bruno Pouliquen, Ralf Steinberger and Camelia Ignat

Named entity and phrase extraction

10.00-10.30: A Framework for Named Entity Recognition in the Open Domain, Richard Evans

10.30-11.00: Phrase Recognition by Filtering and Ranking with Perceptrons, Xavier Carreras and Lluis Marquez

11.00-11.30 Coffee Break


11.30-11.55: Description and Exploitation of BDS: A Syntactic Database about Verb Government in Spanish, Eva Ma. Muniz, Marta Rebolledo, Guillermo Rojo, Ma. Paula Santalla and Susana Sotelo

11.55-12.20: A New Language for Constraint Grammar: Estonian, Kaili Muurisep, Tiina Puolakainen, Kadri Muischnek, Mare Koit, Tiit Roosmaa and Heli Uibo

12.20-12.45:Probabilistic Modelling of Argument Structures Including Non-local Dependencies, Yusuke Miyao, Takashi Ninomiya and Jun'ichi Tsujii

Knowledge acquisition, extraction of terms and named entities

11.30-11.55: Towards a Semantic Extraction of Named Entities, Diana Maynard, Kalina Bontcheva, Hamish Cunningham

11.55-12.20: 1220 A Three-pronged Approach to the Extraction of Key Terms and Semantic Roles, C.D. Paice and W.J. Black

12.20-12.50: Acquisition of Concept Frames: Corpus Extraction and Annotation, Birte Lonneker

12.45-14.30 Lunch
14.30-15.30 Shalom Lappin: A Type-Theoretic Approach to Anaphora and Ellipsis Resolution (invited talk)

Text summarisation

15.30-16.00: Latent Semantic Analysis and the Construction of Coherent Extracts, Tristan Miller

16.00-16.30: Facilitating Email Thread Access by Extractive Summary Generation, Ani Nenkova and Amit Bagga

Part-of-speech tagging

15.30-16.00: Fast and Accurate Part-of-Speech Tagging: The SVM Approach Rev, Jesus Gimenez and Lluis Marques

16.00-16.30: A Metric for the Efficiency of Accurate Tagging Procedures, Antonio Branco and Joao Silva

16.30-17.00 Coffee Break
17.00-18.30 Poster presentations: session 1 (BULGARIA hall lobby)
18.45-20.00 Student presentations (outside the conference programme, BULGARIA hall lobby)


International Conference RANLP-2003 - Programme September 12th (Friday)

9.00-10.00 Stephen Pulman: Learning Domain Theories (invited talk)

Ontology, lexical acquisition

10.00-10.30: Clustering WordNet Word Senses, Eneko Agirre and Oier Lopez de Lacalle

10.30-11.00: Inducing Hyperlinking Rules in Text Collections, Roberto Basili, Maria Teresa Pazienza and Fabio Massimo Zanzotto

Aspects of morphology and applications

10.00-10.30: Guessing Morphological Classes of Unknown German Nouns, Preslav Nakov, Yury Bonev, Galia Angelova, Evelyn Gius and Walther von Hahn

10.30-11.00: Arabic Morpho-syntax for Text-to-Speech, Allan Ramsay and Hanady Mansour

11.00-11.30 Coffee Break

Question Answering, Information extraction, Keyword extraction

11.30-12.00: Socrates - A Question Answering Prototype for Bulgarian, Hristo Tanev

12.00-12.30: Using Parallel Texts to Improve Recall in IE, Mary M. Wood, Susannah J. Lydon, Valentin Tablan, Diana Maynard and Hamish Cunningham

12.30-13.00: Reducing False Positives by Expert Combination in Automatic Keyword Indexing, Anette Hulth

Generation, verb ellipsis resolution, treebanks

11.30-12.00: Near-Synonym Choice in Natural Language Generation, Diana Zaiu Inkpen and Graeme Hirst

12.00-12.30: Using Machine Learning Techniques for VPE detection, Leif Arda Nielsen

12.30-13.00: HPSG-Based Annotation Scheme for Corpora Development and Parsing Evaluation, Kiril Simov

13.00-14.30 Lunch
14.30-15.30 Yorick Wilks: Cross-language algorithms: the progressive conflation of machine translation and information retrieval (invited talk)

Word-sense disambiguation

15.30-16.00: Exploiting Agreement and Disagreement of Human Annotators for Word Sense Disambiguation, Timothy Chklovski and Rada Mihalcea

16.00-16.30: The Role of Non-Ambiguous Words in Natural Language Disambiguation, Rada Mihalcea

Ontologies / Temporal processing

15.30-15.55: Validation and Tuning of WordNet Mapping Techniques, Jordi Daude, Lluis Padro and German Rigau

15.55-16.25: Integrating and Porting knowledge across languages, Jordi Atserias and Luis Villarejo and German Rigau

16.25-16.50: Event Ordering through Temporal Expression Resolution, Estela Saquete, Rafael Munoz and Patricio Matinez-Barco

16.50-17.15 Coffee Break
17.15-18.30 Poster presentations: session 2 (BULGARIA hall lobby)
18.30 Closing

Poster presentations: session 1 September 11th (Thursday)

Is a Biosyntax Possible?, Gemma Bel-Enguix and M. Dolores Jimenez Lopez

RUSLAN as a Semantic Dictionary for Information Extraction, Nina N. Leontyeva

A Grammatical Approach to the Extraction of Index Terms, Jesus Vilares and Miguel A. Alonso

On the Efficient Implementation of German Verb Placement in HPSG, Berthold Crysmann

Creating Syntactically Annotated Romanian Corpus, Victoria Bobicev

Topological Fields Chunking for German with SVM's: Optimizing SVM-parameters with GA's, Martina Liepert

Integrating Shallow and Deep NLP for Information Extraction, Feiyu Xu and Hans-Ulrich Krieger

A Type-Driven Method for Compacting MMorph Resources, Hans-Ulrich Krieger and Feiyu Xu

The Effects of Prosody on Segmental Variation, Kyuchul Yoon

Real-Time Evaluation Architecture for MT Using Multiple Backward Translations, Keiji Yasuda, Eiichiro Sumita, Genichiro Kikui, Seiichi Yamamoto, Masuzo Yanagida

Topic-adaptation of Pattern-based MT Systems Using Feedback Cleaning, Michael Paul, Kenji Imamura, Eiichiro Sumita and Seiichi Yamamoto

Automatic Proficiency Level Checking based on SST Corpus, Thepchai Supnithi, Kiyotaka Uchimoto, Toyomi Saiga, Emi Izumi, Sornlertlamvanich Virach and Hitoshi Isahara

Weighting Distributional Features for Automatic Semantic Classification of Words, Viktor Pekar and Michael Krkoska

Filtering Text and Instanciation of Coherent Summaries: A Rhetorical Schema Based Approach, Mariem Ellouze and Abdelmajid Ben Hamadou

Aspect and the Semantics-Pragmatics Interface, Barbara Sonnenhauser

Data-Oriented Paraphrasing, Andrew Finch, Taro Watanabe and Eiichiro Sumita

A Methodology for Semantically Annotating a Corpus Using a Domain Ontology and Machine Learning, Alexandros Valarakos, Georgios Sigletos, Vangelis Karkaletsis and Georgios Paliouras

Statistics of Morphological Finite-State Transition Networks Obey the Power Law, Alexander Troussov and Brian O'Donovan

Automatic Acquisition of Word Selection Restrictions: A Stochastic Approach, Veska Noncheva, Pablo Gamallo, Alexandre Agustini and Gabriel Lopes

Stomp, a POS-tagger with a Different View, Jonas Sjobergh


Poster presentations: session 2 September 12th (Friday)

Topic- and Author-Specific Suggestion Lists for Typing with Ambiguous Keyboards, Karin Harbusch, Sasa Hasan, Hajo Hoffmann, Michael Kuhn Bernhard Schuler

A Hybrid NLP System for NLIs, Montserrat Marimon and Nuria Bel

Architecture of a Multi-modal Dialogue System Oriented to Multilingual Question-answering, Rafael M. Terol, Patricio Martinez-Barco and Manuel Palomar

A Method for Observing Terminological Evolution, Annie Tartier

English Adverbial NPs of Time in Machine Translation, Gabor L. Ugray, Gabor Ujvarosi

Preparation for POS Tagging of Croatian Using CLaRK System, Marko Tadic, Bozo Bekavac

Human Centred Evaluation of coherence and cohesion in automatic extracts, Constantin Orasan

Do we Correctly Count the Term Frequency? The Influence of Anaphoric Expressions of Terms in Automatic Term Extraction, Le An Ha

Semantic Annotation of Named Entities using Ontology and Massive World-Knowledge, Borislav Popov, Atanas Kiryakov, Dimitar Manov, Angel Kirilov, Damyan Ognyanoff, Miroslav Goranov

Multi-lingual Response Generator for Spoken Dialogue Systems: Database Approach, Marcela Charfuelan, Holmer Hemsen and Marnie Lai

Development of Language Resources for Speech-to-Speech Translation, Victoria Arranz, Nuria Castell and Jesus Gimenez

Tagging a Spontaneous Speech Corpus of Spanish, Antonio Moreno and Jose M. Guirao

Automatic Sense (Pre)tagging by Syntagmatic Patterns, Iulia Nica, M. Antonia Marti i Antonin and Andres Montoyo

Automatic Extraction of Meta-descriptors for Text Description, Nicolas Hernandez and Brigitte Grau