Workshop "Toward Computational Models of Literary Analysis" May 22nd, 2006, Genova (Italy), Home Page: http://ai-nlp.info.uniroma2.it/basili/LREC2006/TowardsCompModels.html jointly held with the International Conference on LANGUAGE RESOURCES AND EVALUATION, LREC 2006 May 22nd-28th, 2006 CALL FOR PAPERS Motivations It has been often noticed that computer based literary critics is still relying on studies of concordances as traditionally intended since the 13th century. All the intermediate digital representations (storage, indexes, data structures or records) are not capitalized although they can play the role of a new literary "monster" (like the Cheiron centaur) as a new meaningful, artistic and hermeneutic macro unit. It is indeed true that the digital representation, its metadata and its digital derivatives (e.g. indexes, parse trees, semantic references to external dictionaries) are new and more complex forms of "concordances" and should be used by the literary scholar in cooperation with the original content. New processes of narrative analysis should thus take all of this into account by exploiting the fruitful interactions among the parts of the monster within suitable software architectures (that are thus more complex than digital archives/catalogs). In the Natural Language Processing research community, a wide range of computational methods have been successfully applied to information and document management, spanning from text categorization and information extraction, to ontology leaning, text mining and automatic semantic markup. Although these techniques are mostly applied to technical texts in application-driven contexts, their application range could be expanded to encompass a larger typology of texts, thereby gaining new powerful insights for the analysis of literary text content and paving the way for new experiments and forms of text hermeneutics. The development of language resources in this area is also rather limited and more interdisciplinary research is needed to open the field to realistic and effective applications. Workshop Aims The long term research enterprise in this field should aim to design novel paradigms for literary studies that are: - more information-centered, as they work at a higher level of abstraction - interactive with the scholar, as the software is proactive with respect to the literary work - multifunctional and integrated as they support incremental refinement of internal knowledge of the opera along with more interaction with the expert takes place. This workshop aims to gather studies, achievements and experiences from scholars belonging to different schools (literary studies, linguistics, computing technologies, artificial intelligence, human-computer interaction) in order to survey, compare and assess currently independent research enterprises whose focus is narrative and literary text analysis. The aim is to discuss at which extent the textual evidences currently observable through digital technologies can support the computational treatment of narrative and literary phenomena. Results in these area have an invaluable impact on the technological side (as a novel challenge for computational models of language and narrative) as well as on the cultural side (as new perspectives for human-computer interaction and modern literary analysis). Moreover, the enormous potentials offered to cultural heritage preservation and dissemination are evident. Topics The topics addressed by the workshop are not exhaustively listed as follows: - Narrative Models for Human-Computer Interaction - Text Mining for Analysis of narrative and literary texts - Machine Learning and Knowledge Acquisition from literary texts - Literary Corpora and Resources - Ontologies of narrative phenomena - Cognitive Models of aesthetics - Semantic annotations of literary corpora Workshop format. The workshop will be a half-day event with position statements from invited speakers with remaining time for presentations of scientific papers. Submissions are intended to present works in progress and more completed works which fall within the scope defined by the topics listed above. A final 1 hour open discussion among all the workshop participants will be moderated by the organizers. Submission Position papers (orientative length: 1000 words) are invited about studies, achievements and experiences from scholars from different areas (narrative analysis, literary studies, linguistics, computing technologies, artificial intelligence) aiming to survey, compare and assess currently independent research enterprises whose focus is narrative and literary text analysis. Each submission should show: title; author(s); affiliation(s); and contact author's e-mail address, postal address, telephone and fax numbers. Submissions must be sent electronically in PDF to the following address: Roberto Basili, basili@info.uniroma2.it Important dates: Submission of papers: February 24th, 2006 Acceptance Notification: March 10th, 2006 Preliminary Program: March 25th, 2006 Submission of the final version of paper: April 5th, 2006 Workshop : May 22nd, 2006 Organising Committee ================== Roberto Basili (University of Roma Tor Vergata, Italy) (co-chair) Simonetta Bassi (University of Pisa & SIGNUM, SNS, Italy) Marc Cavazza (University of Teeside, UK) Richard Coyne (University of Edinburgh, UK) Pierantonio Frare (University of Milan, Italy) Andrea Gareffi (University of Roma, Tor Vergata, Italy) Graeme Hirst, (University of Toronto, Canada) Jerry Hobbs (ISI, University of Southern California, USA) Hugh Craig (University of Newcastle, Australia) Alessandro Lenci (University of Pisa, Italy) (co-chair) Marco Pennacchiotti (University of Roma, Tor Vergata, Italy) Mirko Tavoni (University of Pisa, Italy) Yorick Wilks (University of Sheffield, UK) For any information related to the organization, please contact: Roberto Basili e-mail: basili@info.uniroma2.it Dept. of Computer Science, Systems and Management University of Roma Tor Vergata Via di Tor Vergata 00133 Roma (ITALY) tel: +39 06 72597391 fax: +39 06 72597460