Computational Linguistics and Intelligent Text Processing

1. Front Matter

   PDF

2. Trends and Opportunities

   1. Has Computational Linguistics Become More Applied?

      • Kenneth Church

      Pages 1-5

   2. Opportunities for Natural Language Processing Research in Education

      • Jill Burstein

      Pages 6-27

3. Linguistic Knowledge Representation Formalisms

   1. Information Structure in a Formal Framework

      • Maarika Traat

      Pages 28-40

   2. A Karaka Based Annotation Scheme for English

      • Ashwini Vaidya, Samar Husain, Prashanth Mannem, Dipti Misra Sharma

      Pages 41-52

4. Corpus Analysis and Lexical Resources

   1. Substring Statistics

      • Kyoji Umemura, Kenneth Church

      Pages 53-71

   2. Evaluation of the Syntactic Annotation in EPEC, the Reference Corpus for the Processing of Basque

      • Larraitz Uria, Ainara Estarrona, Izaskun Aldezabal, Maria Jesús Aranzabe, Arantza Díaz de Ilarraza, Mikel Iruskieta

      Pages 72-85

   3. Reducing Noise in Labels and Features for a Real World Dataset: Application of NLP Corpus Annotation Methods

      • Rebecca J. Passonneau, Cynthia Rudin, Axinia Radeva, Zhi An Liu

      Pages 86-97

   4. Unsupervised Classification of Verb Noun Multi-Word Expression Tokens

      • Mona T. Diab, Madhav Krishna

      Pages 98-110

5. Extraction of Lexical Knowledge

   1. Semantic Mapping for Related Term Identification

      • Rafael E. Banchs

      Pages 111-124

   2. An Improved Automatic Term Recognition Method for Spanish

      • Alberto Barrón-Cedeño, Gerardo Sierra, Patrick Drouin, Sophia Ananiadou

      Pages 125-136

   3. Bootstrapping a Verb Lexicon for Biomedical Information Extraction

      • Giulia Venturi, Simonetta Montemagni, Simone Marchi, Yutaka Sasaki, Paul Thompson, John McNaught et al.

      Pages 137-148

   4. TermeX: A Tool for Collocation Extraction

      • Davor Delač, Zoran Krleža, Jan Šnajder, Bojana Dalbelo Bašić, Frane Šarić

      Pages 149-157

6. Morphology and Parsing

   1. Guessers for Finite-State Transducer Lexicons

      • Krister Lindén

      Pages 158-169

   2. Combining Language Modeling and Discriminative Classification for Word Segmentation

      • Dekang Lin

      Pages 170-182

   3. Formal Grammar for Hispanic Named Entities Analysis

      • Grettel Barceló, Eduardo Cendejas, Grigori Sidorov, Igor A. Bolshakov

      Pages 183-194

   4. Automatic Extraction of Clause Relationships from a Treebank

      • Oldřich Krůza, Vladislav Kuboň

      Pages 195-206

   5. A General Method for Transforming Standard Parsers into Error-Repair Parsers

      • Carlos Gómez-Rodríguez, Miguel A. Alonso, Manuel Vilares

      Pages 207-219

7. Semantics

   1. Topic-Focus Articulation from the Semantic Point of View

      • Marie Duží

      Pages 220-232

   2. The Value of Weights in Automatically Generated Text Structures

      • Dana Dannélls

      Pages 233-244

th CICLing 2009 markedthe 10 anniversary of the Annual Conference on Intel- gent Text Processing and Computational Linguistics. The CICLing conferences provide a wide-scope forum for the discussion of the art and craft of natural language processing research as well as the best practices in its applications. This volume contains ?ve invited papers and the regular papers accepted for oral presentation at the conference. The papers accepted for poster presentation were published in a special issue of another journal (see the website for more information). Since 2001, the proceedings of CICLing conferences have been published in Springer’s Lecture Notes in Computer Science series, as volumes 2004, 2276, 2588, 2945, 3406, 3878, 4394, and 4919. This volume has been structured into 12 sections: – Trends and Opportunities – Linguistic Knowledge Representation Formalisms – Corpus Analysis and Lexical Resources – Extraction of Lexical Knowledge – Morphology and Parsing – Semantics – Word Sense Disambiguation – Machine Translation and Multilinguism – Information Extraction and Text Mining – Information Retrieval and Text Comparison – Text Summarization – Applications to the Humanities A total of 167 papers by 392 authors from 40 countries were submitted for evaluation by the International Program Committee, see Tables 1 and 2. This volume contains revised versions of 44 papers, by 120 authors, selected for oral presentation; the acceptance rate was 26. 3%.

• NLP
• Processing
• Web mining
• algorithmic learning
• computational linguistics
• document analysis
• human language technologies
• information extraction
• knowledge bases
• linguistics
• machine learning
• machine translation
• natural language generation
• natural language processing
• par

• National Polytechnic Institute, Center for Computing Research, Mexico City, Mexico

  Alexander Gelbukh

Policies and ethics