CNRS, LIF, Marseille
Scope and Topics
The aim of this workshop is to foster interactions among researchers and practitioners in Natural Language Processing (NLP) working within the paradigm of Cognitive Science. Research into NLP involves concepts and methods from many fields including artificial intelligence, linguistics, computational linguistics, statistics, computer science, and most importantly cognitive science. Because it is impossible to cover all aspects of NLP this workshop emphasises the contribution of cognitive science to language processing, including conceptualisation, representation, discourse processing, meaning construction, ontology building, and text mining.
Topics of interest include, but are not limited to:
- Cognitive and Psychological Models of NLP
- Computational Models of NLP
- Evolutionary NLP
- Situated (embodied) NLP
- Multimodality in speech / text processing
- Text Summarization and Information Extraction
- Natural Language Interfaces and Dialogue Systems
- Multi-Lingual Processing
- Pragmatics and NLP
- Speech Processing
- Tools and Resources in NLP
- Text Mining
- Electronic Dictionaries
- Evaluation of NLP Systems
These topics can be addressed from any of the following perspectives: full automation
by machines for machine (traditional NLP or HLT), semi-automated processing
, i.e. machine-mediated
processing (programs assisting people in their tasks), simulation of human
Patrick W. Hanks, Charles University in Prague, Czech Republic
TITLE: Making meanings
This presentation describes a long-term research project, Corpus Pattern Analysis (CPA), whose goals include: a) shedding light on how people use words to make meanings and b) creating an infrastructure resource that will support such tasks as the interpretation of meanings in texts and the generation of idiomatic phraseology.
Traditionally, the methodology of word sense disambiguation (WSD) takes an inventory of word senses from a dictionary such as LDOCE and then seeks contextual criteria for the realization of each sense. It is now acknowledged by some of the leading practitioners in the field (e.g. Ide and Wilks 2006) that this procedure has been a failure. One reason for this failure, it seems from the perspective of corpus linguistics, is excessive reliance on reductionist theories of compositionality. Another is failure to pay sufficient attention to the phenomenon of collocation. Another is an expectation of certainty, for in matters of meaning only probabilities may be expected.
CPA reverses the whole WSD methodology. It builds from the bottom up. It starts by identifying the patterns of normal usage that are associated with each word, through painstaking analysis of corpus data. Only when the patterns have been established is an attempt made to interpret them. Meanings, in the form of statements about implicatures, are attached to patterns, not to words in isolation.
Among the findings of CPA that will be discussed in this presentation are:
- Empirical support for Sinclair´s (1991, 1998) distinction between “the phraseological tendency” and “the terminological tendency”
- The need for a new, empirically well founded theory of language that takes account of phraseological norms and semantic/pragmatic exploitations
- The relationship between creative language use (including metaphor) and conventional language use.
The Theory of Norms and Exploitations is a “double-helix” theory of rule-governed linguistic behaviour. It has its roots in an obscure paper by Hanks (1994).
Hanks, Patrick. 1994. ‘Linguistic norms and pragmatic explanations, or why lexicographers need prototype theory and vice versa’. In F. Kiefer, G. Kiss, and J. Pajzs (eds.), Papers in Computational Lexicography: Complex ‘94. Research Institute for Linguistics, Hungarian Academy of Sciences. Anthologized in Hanks (ed., 2008).
Hanks, Patrick (ed.). 2008. Lexicology: Critical Concepts in Linguistics. 6 volumes. Routledge.
Ide, Nancy, and Wilks, Yorick. 2005. ‘Making sense about sense’. In Eneko Agirre and Philip Edmonds (eds.), Word sense disambiguation. Kluwer.
Sinclair, John. 1991. Corpus, Concordance, Collocation. Oxford University Press.
Sinclair, John. 1998. ‘The lexical item’ in E. Weigand (ed.), Contrastive Lexical Semantics. Benjamins. Anthologized in Hanks (ed. 2008)
Workshop Program Committee
S. Anfantenos, IRIT, University of Toulouse 3, France
M. Aretoulaki, Dialogconnection.com, U.K.
J. Barnden, Birmingham University, U.K.
D. Cristea, University "A.I.Cuza" of Iasi, Romania
C. Day, Keele University, U.K.
R. Delmonte, University of Texas, U.S.A.
B. Endres-Niggemeyer, Fachhochschule Hanover, Germany
O. Ferret, CEA, France
I. Fischer, University of Konstanz, Germany
S. Helmreich, New Mexico State University, U.S.A.
N. Hernandez, LINAS, University of Nantes, France
C. A. Higgins, Nottingham University, U.K.
E. W. Hinrichs, University of Tuebingen, Germany
O. Kutz, University of Bremen, Germany
G. Lapalme, University of Montréal, Canada
D. Mladenic, J. Stefan Institute, Slovenia
D. Molla, Macquarie University, Sydney, Australia
W. R. Murray, Boeing Research and Technology, U.S.A.
N. Nicolov, J.D. Power and Associates, U.S.A.
T. Poibeau, CNRS, LIPN university of Paris-13, France
B. R. Rapp, GRLC, Tarragona, Spain
P. Rayson, Lancaster University, U.K.
F. Ren, University of Tokushima, Japan
C. Roche, Université de Savoie, France
S. Russell, University of New Hampshire, U.S.A.
R. Schwitter, Macquarie University, Sydney, Australia
F. Sedes, Université de Toulouse, France
G. Serasset, CLIPS-IMAG, Grenoble, France
B. Sharp, Staffordshire University, U.K.
C. Soule-Dupuy, Université de Toulouse, France
D. Schwab, LIG-GETALP, Grenoble, France
G. Thompson, Liverpool University, U.K.
D. Tufis, University "A.I.Cuza" of Iasi, Romania
T. Wandmacher, CEA, Fontenay-aux-Roses, France
Y. Wilks, Sheffield University, U.K.
P. Windridge, Staffordshire University, U.K.
M. Zock, LIF-CNRS, Marseille, France
All accepted papers will be published in the workshop proceedings book, under an ISBN reference, and on CD-ROM support.