Computational Linguistics -- Starting with Complex Primitives Pays Off -- Things Are Not Always Equal -- GIGs: Restricted Context-Sensitive Descriptive Power in Bounded Polynomial-Time -- Total Lexicalism and GASGrammars: A Direct Way to Semantics -- Pseudo Context-Sensitive Models for Parsing Isolating Languages: Classical Chinese — A Case Study -- Imperatives as Obligatory and Permitted Actions -- Formal Representation and Semantics of Modern Chinese Interrogative Sentences -- Analyzing V+Adj in Situation Semantics -- Diagnostics for Determining Compatibility in English Support-Verb-Nominalization Pairs -- A Maximum Entropy Approach for Spoken Chinese Understanding -- A Study to Improve the Efficiency of a Discourse Parsing System -- Conversion of Japanese Passive/Causative Sentences into Active Sentences Using Machine Learning -- From Czech Morphology through Partial Parsing to Disambiguation -- Fast Base NP Chunking with Decision Trees - Experiments on Different POS Tag Settings -- Guaranteed Pre-tagging for the Brill Tagger -- Performance Analysis of a Part of Speech Tagging Task -- An Efficient Online Parser for Contextual Grammars with at Most Context—Free Selectors -- Offline Compilation of Chains for Head-Driven Generation with Constraint-Based Grammars -- Generation of Incremental Parsers -- Computing with Realizational Morphology -- Approach to Construction of Automatic Morphological Analysis Systems for Inflective Languages with Little Effort -- Per-node Optimization of Finite-State Mechanisms for Natural Language Processing -- An Evaluation of a Lexicographer’s Workbench Incorporating Word Sense Disambiguation -- Using Measures of Semantic Relatedness for Word Sense Disambiguation -- Automatic Sense Disambiguation of the Near-Synonyms in a Dictionary Entry -- Word Sense Disambiguation for Untagged Corpus: Application to Romanian Language -- Automatic Noun Sense Disambiguation -- Tool for Computer-Aided Spanish Word Sense Disambiguation -- Augmenting WordNet’s Structure Using LDOCE -- Building Consistent Dictionary Definitions -- Is Shallow Parsing Useful for Unsupervised Learning of Semantic Clusters? -- Experiments on Extracting Semantic Relations from Syntactic Relations -- A Method of Automatic Detection of Lexical Relationships Using a Raw Corpus -- Sentence Co-occurrences as Small-World Graphs: A Solution to Automatic Lexical Disambiguation -- Dimensional Analysis to Clarify Relations among the Top-Level Concepts of an Upper Ontology: Process, Event, Substance, Object -- Classifying Functional Relations in Factotum via WordNet Hypernym Associations -- Processing Natural Language without Natural Language Processing -- The Design, Implementation, and Use of the Ngram Statistics Package -- An Estimate Method of the Minimum Entropy of Natural Languages -- A Corpus Balancing Method for Language Model Construction -- Building a Chinese Shallow Parsed TreeBank for Collocation Extraction -- Corpus Construction within Linguistic Module of City Information Dialogue System -- Diachronic Stemmed Corpus and Dictionary of Galician Language -- Can We Correctly Estimate the Total Number of Pages in Google for a Specific Language? -- The Word Is Mightier than the Count: Accumulating Translation Resources from Parsed Parallel Corpora -- Identifying Complex Sound Correspondences in Bilingual Wordlists -- Generating Texts with Style -- Multilingual Syntax Editing in GF -- QGen— Generation Module for the Register Restricted InBASE System -- Towards Designing Natural Language Interfaces -- A Discourse System for Conversational Characters -- A Portable Natural Language Interface for Diverse Databases Using Ontologies -- Time-Domain Structural Analysis of Speech -- Experiments with Linguistic Categories for Language Model Optimization -- Chinese Utterance Segmentation in Spoken Language Translation -- Intelligent Text Processing -- Using Natural Language Processing for Semantic Indexing of Scene-of-Crime Photographs -- Natural Language in Information Retrieval -- Natural Language System for Terminological Information Retrieval -- Query Expansion Based on Thesaurus Relations: Evaluation over Internet -- Suggesting Named Entities for Information Access -- Probabilistic Word Vector and Similarity Based on Dictionaries -- Web Document Indexing and Retrieval -- Event Sentence Extraction in Korean Newspapers -- Searching for Significant Word Associations in Text Documents Using Genetic Algorithms -- Cascaded Feature Selection in SVMs Text Categorization -- A Study on Feature Weighting in Chinese Text Categorization -- Experimental Study on Representing Units in Chinese Text Categorization -- Partitional Clustering Experiments with News Documents -- Fast Clustering Algorithm for Information Organization -- Automatic Text Summarization of Scientific Articles Based on Classification of Extract’s Population -- Positive Grammar Checking:A Finite State Approach.

CICLing 2003 (www.CICLing.org) was the 4th annual Conference on Intelligent Text Processing and Computational Linguistics. It was intended to provide a balanced view of the cutting-edge developments in both the theoretical foundations of computational linguistics and the practice of natural language text processing with its numerous applications. A feature of CICLing conferences is their wide scope that covers nearly all areas of computational linguistics and all aspects of natural language processing applications. The conference is a forum for dialogue between the specialists working in these two areas. This year we were honored by the presence of our keynote speakers Eric Brill (Microsoft Research, USA), Aravind Joshi (U. Pennsylvania, USA), Adam Kilgarriff (Brighton U., UK), and Ted Pedersen (U. Minnesota, USA), who delivered excellent extended lectures and organized vivid discussions. Of 92 submissions received, after careful reviewing 67 were selected for presentation; 43 as full papers and 24 as short papers, by 150 authors from 23 countries: Spain (23 authors), China (20), USA (16), Mexico (13), Japan (12), UK (11), Czech Republic (8), Korea and Sweden (7 each), Canada and Ireland (5 each), Hungary (4), Brazil (3), Belgium, Germany, Italy, Romania, Russia and Tunisia (2 each), Cuba, Denmark, Finland and France (1 each).