Table of contents
Editors' Foreword
Part I. Computation for linguistics
Linguistic challenges for computationalists
Part II. Information extraction & indexing
NLP: An information extraction perspective
Semantic indexing using minimum redundancy cut in ontologies
Indexing and querying linguistic metadata and document content
Term representation with Generalized Latent Semantic Analysis
Part III. Parsing
Multilingual dependency parsing: A pipeline approach
How does treebank annotation influence parsing? Or how not to compare apples and oranges
The SenSem project: Syntactico-semantic annotation of sentences in Spanish
Part IV. Anaphora & referring expressions
Generating referring expressions: Past, present and future
A data-driven approach to pronominal anaphora resolution for German
Part V. Classification
Efficient spam analysis for weblogs through URL segmentation
Document classification using semantic networks with an adaptive similarity measure
Text summarization for improved text classification
Exploiting linguistic cues to classify rhetorical relations
Part VI. Textual entailment & question answering
Tree edit distance for textual entailment
A genetic algorithm for optimising information retrieval with linguistic features in question answering
Lexico-syntactic subsumption for textual entailment
A knowledge-based approach to text-to-text similarity
Part VII. Ontologies
A simple WWW-based method for semantic word class acquisition
Automatic building of Wordnets
Part VIII. Machine translation
Lexical transfer selection using annotated parallel corpora
Multi-perspective evaluation of the FAME speech-to-speech translation system for Catalan, English and Spanish
Parallel corpora for medium density languages
Part IX. Corpora
The role of data in NLP: The case for dataset profiling
Even very frequent function words do not distribute homogeneously
Exploiting parallel texts to produce a multilingual sense tagged corpus for word sense disambiguation
Detecting dangerous coordination ambiguities using word distribution
List and addresses of contributors
Index of subjects and terms
This article is available free of charge.