Computational Linguistics and Intelligent Text Processing: 4th International Conference, CICLing 2003 Mexico City, Mexico, February 16–22, 2003 Proceedings

Aravind K. Joshi (auth.), Alexander Gelbukh (eds.)3540005323, 9783540005322

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).

---

Table of contents :
An Efficient Online Parser for Contextual Grammars with at Most Context—Free Selectors….Pages 168-179
Offline Compilation of Chains for Head-Driven Generation with Constraint-Based Grammars….Pages 180-190
Generation of Incremental Parsers….Pages 191-202
Computing with Realizational Morphology….Pages 203-214
Starting with Complex Primitives Pays Off….Pages 1-10
Things Are Not Always Equal….Pages 11-21
GIGs: Restricted Context-Sensitive Descriptive Power in Bounded Polynomial-Time….Pages 22-35
Total Lexicalism and GASGrammars: A Direct Way to Semantics….Pages 36-47
Pseudo Context-Sensitive Models for Parsing Isolating Languages: Classical Chinese — A Case Study….Pages 48-51
Imperatives as Obligatory and Permitted Actions….Pages 52-64
Formal Representation and Semantics of Modern Chinese Interrogative Sentences….Pages 65-74
Analyzing V+Adj in Situation Semantics….Pages 75-84
Diagnostics for Determining Compatibility in English Support-Verb-Nominalization Pairs….Pages 85-90
A Maximum Entropy Approach for Spoken Chinese Understanding….Pages 91-100
A Study to Improve the Efficiency of a Discourse Parsing System….Pages 101-114
Conversion of Japanese Passive/Causative Sentences into Active Sentences Using Machine Learning….Pages 115-125
From Czech Morphology through Partial Parsing to Disambiguation….Pages 126-135
Fast Base NP Chunking with Decision Trees – Experiments on Different POS Tag Settings….Pages 136-147
Guaranteed Pre-tagging for the Brill Tagger….Pages 148-157
Performance Analysis of a Part of Speech Tagging Task….Pages 158-167
Approach to Construction of Automatic Morphological Analysis Systems for Inflective Languages with Little Effort….Pages 215-220
Per-node Optimization of Finite-State Mechanisms for Natural Language Processing….Pages 221-224
An Evaluation of a Lexicographer’s Workbench Incorporating Word Sense Disambiguation….Pages 225-240
Using Measures of Semantic Relatedness for Word Sense Disambiguation….Pages 241-257
Automatic Sense Disambiguation of the Near-Synonyms in a Dictionary Entry….Pages 258-267
Word Sense Disambiguation for Untagged Corpus: Application to Romanian Language….Pages 268-272
Automatic Noun Sense Disambiguation….Pages 273-276
Tool for Computer-Aided Spanish Word Sense Disambiguation….Pages 277-280
Augmenting WordNet’s Structure Using LDOCE….Pages 281-294
Building Consistent Dictionary Definitions….Pages 295-303
Is Shallow Parsing Useful for Unsupervised Learning of Semantic Clusters?….Pages 304-313
Experiments on Extracting Semantic Relations from Syntactic Relations….Pages 314-324
A Method of Automatic Detection of Lexical Relationships Using a Raw Corpus….Pages 325-328
Sentence Co-occurrences as Small-World Graphs: A Solution to Automatic Lexical Disambiguation….Pages 329-332
Dimensional Analysis to Clarify Relations among the Top-Level Concepts of an Upper Ontology: Process, Event, Substance, Object ….Pages 333-346
Classifying Functional Relations in Factotum via WordNet Hypernym Associations….Pages 347-359
Processing Natural Language without Natural Language Processing….Pages 360-369
The Design, Implementation, and Use of the Ngram Statistics Package….Pages 370-381
An Estimate Method of the Minimum Entropy of Natural Languages….Pages 382-392
A Corpus Balancing Method for Language Model Construction….Pages 393-401
Time-Domain Structural Analysis of Speech….Pages 506-510
Experiments with Linguistic Categories for Language Model Optimization….Pages 511-515
Chinese Utterance Segmentation in Spoken Language Translation….Pages 516-525
Building a Chinese Shallow Parsed TreeBank for Collocation Extraction….Pages 402-405
Corpus Construction within Linguistic Module of City Information Dialogue System….Pages 406-409
Diachronic Stemmed Corpus and Dictionary of Galician Language….Pages 410-414
Can We Correctly Estimate the Total Number of Pages in Google for a Specific Language?….Pages 415-419
Towards Designing Natural Language Interfaces….Pages 477-489
A Discourse System for Conversational Characters….Pages 490-493
A Portable Natural Language Interface for Diverse Databases Using Ontologies….Pages 494-505
The Word Is Mightier than the Count: Accumulating Translation Resources from Parsed Parallel Corpora….Pages 420-431
Identifying Complex Sound Correspondences in Bilingual Wordlists….Pages 432-443
Generating Texts with Style….Pages 444-452
Multilingual Syntax Editing in GF….Pages 453-464
QGen— Generation Module for the Register Restricted InBASE System….Pages 465-476
Using Natural Language Processing for Semantic Indexing of Scene-of-Crime Photographs….Pages 526-536
Natural Language in Information Retrieval….Pages 537-540
Natural Language System for Terminological Information Retrieval….Pages 541-552
Query Expansion Based on Thesaurus Relations: Evaluation over Internet….Pages 553-556
Suggesting Named Entities for Information Access….Pages 557-561
Probabilistic Word Vector and Similarity Based on Dictionaries….Pages 562-572
Web Document Indexing and Retrieval….Pages 573-579
Event Sentence Extraction in Korean Newspapers….Pages 580-583
Searching for Significant Word Associations in Text Documents Using Genetic Algorithms….Pages 584-587
Cascaded Feature Selection in SVMs Text Categorization….Pages 588-591
A Study on Feature Weighting in Chinese Text Categorization….Pages 592-601
Experimental Study on Representing Units in Chinese Text Categorization….Pages 602-614
Partitional Clustering Experiments with News Documents….Pages 615-618
Fast Clustering Algorithm for Information Organization….Pages 619-622
Automatic Text Summarization of Scientific Articles Based on Classification of Extract’s Population….Pages 623-634
Positive Grammar Checking:A Finite State Approach….Pages 635-646