RANLP 2003: Borovets, Bulgaria

Invited Lectures

• Chris Fox, Shalom Lappin: A type-theoretic approach to anaphora and ellipsis resolution. 1-16
• Yorick Wilks, Nick Webb, Andrea Setzer, Mark Hepple, Roberta Catizone: Human dialogue modelling using machine learning. 17-28
• Stephen G. Pulman, Maria Liakata: Learning domain theories. 29-44
• Inderjeet Mani: Recent developments in temporal information extraction. 45-60
• Branimir Boguraev: Annotation-based finite state processing in a large-scale NLP arhitecture. 61-80

Lexical semantics and lexical knowledge acquisition

• Oren Glickman, Ido Dagan: Acquiring lexical paraphrases from a single corpus. 81-90
• Violeta Seretan, Luka Nerima, Eric Wehrli: Multi-word collocation extraction by syntactic composition of collocation bigrams. 91-100
• Peter D. Turney, Michael L. Littman, Jeffrey Bigham, Victor Shnayder: Combining independent modules in lexical multiple-choice problems. 101-110
• Mario Jarmasz, Stan Szpakowicz: Roget's thesaurus and semantic similarity. 111-120
• Eneko Agirre, Oier Lopez de Lacalle: Clustering WordNet word senses. 121-130
• Roberto Basili, Maria Teresa Pazienza, Fabio Massimo Zanzotto: Inducing hyperlinking rules in text collections. 131-140
• Diana Zaiu Inkpen, Graeme Hirst: Near-synonym choice in natural language generation. 141-152

Tagging, parsing and syntax

• Jesús Giménez, Lluís Màrquez: Fast and accurate part-of-speech tagging: The SVM approach revisited. 153-163
• Virginia Savova, Leonid Peshkin: Part-of-speech tagging with minimal lexicalization. 163-172
• António Horta Branco, João Ricardo Silva: Accurate annotation: An efficiency metric. 173-182
• Mary Hearne, Khalil Sima'an: Structured parameter estimation for LFG-DOP. 183-192
• Sandra Kübler: Parsing without grammar - Using complete trees instead. 193-204
• Xavier Carreras, Lluís Màrquez: Phrase recognition by filtering and ranking with perceptrons. 205-216
• Sebastian van Delden, Fernando Gomez: Cascaded finite-state partial parsing: A larger-first approach. 217-226
• Henning Christiansen: A constraint-based bottom-up counterpart to definite clause grammars. 227-236

Information extraction

• Mary McGee Wood, Susannah J. Lydon, Valentin Tablan, Diana Maynard, Hamish Cunningham: Using parallel texts to improve recall in botany. 237-246
• Elena Filatova, Vasileios Hatzivassiloglou: Marking atomic events in sets of related texts. 247-256
• Svetla Boytcheva, Milena Yankova, Albena Strupchanska: Semantically driven approach for scenario recognition in the IE system FRET. 257-266
• Richard J. Evans: A framework for named entity recognition in the open domain. 267-276

Text Summarisation and Document Processing

• Tristan Miller: Latent semantic analysis and the construction of coherent extracts. 277-286
• Ani Nenkova, Amit Bagga: Facilitating email thread access by extractive summary generation. 287-296
• Preslav Nakov, Elena Valchanova, Galia Angelova: Towards deeper understanding of the latent semantic analysis performance. 297-306
• Bruno Pouliquen, Ralf Steinberger, Camelia Ignat: Automatic linking of similar texts across languages. 307-316

Other NLP topics

• Leif Arda Nielsen: Verb phrase ellipsis detection using machine learning techniques. 317-326
• Kiril Ivanov Simov: HPSG-based annotation scheme for corpora development and parsing evaluation. 327-336
• Allan Ramsay, Hanady Mansour: Arabic Morpho-syntax for Text-to-Speech. 337-346
• Preslav Nakov, Yury Bonev, Galia Angelova, Evelyn Gius, Walther von Hahn: Guessing morphological classes of unknown German nouns. 347-356
• Rada Mihalcea, Timothy Chklovski: Building sense tagged corpora with volunteer contributions over the Web. 357-366
• Anette Hulth: Reducing false positives by expert combination in automatic keyword indexing. 367-376
• Hristo Tanev: Socrates: A question answering prototype for Bulgarian. 377-386
• Rada Mihalcea: Unsupervised natural language disambiguation using non-ambiguous words. 387-396