Andersen, Peter Břgh - Professor at the University of Aalborg in Denmark, whose research focuses on computational semiotics. Papers and descriptions of current research.
Books on Computational Semantics - Two draft online textbooks in PostScript format, by Patrick Blackburn and Johan Bos. Also features an online Prolog tutorial.
British National Corpus - A balanced synchronic text corpus containing 100 million words with morphosyntactic annotation.
Corpus-Based Computational Linguistics Resources - An annotated list of resources in this field and the allied discipline of statistical natural language processing. Corpora, tools, literature and other resources.
Definition of Computational Semiotics - A concise outline of this field from the perspective of defining knowledge units for artificial intelligence systems.
EuroWordNet - A project to compile compatible wordnets for seven European languages. Documentation, project reports, and downloadable database samples.
Global Wordnet Association - A society dedicated to the collection and standardization of wordnets, corpora, and other basic language processing tools. List of current and pending wordnets.
Hermit Crab - A morphological parser and generator, developed for classical generative phonology and morphology. Download, documentation, background information and computational morphology research.
ILK: Induction of Linguistic Knowledge - A research program at Tilburg University in the Netherlands, aimed at using inductive learning technology to advance both language engineering and the understanding of linguistic knowledge. Publications, downloadable software, and text analysis demos.
InDiGen: Integrated Discourse Generation - A research project which aims to bring about "an integrated approach to discourse and sentence planning which captures the interaction of discourse marker selection, ellipsis, and discourse structure." Includes related publications, web-based demo.
Introduction to Computational Phonology - Brief course on the fundamentals of this field, by Dafydd Gibbon. Includes basics of computing phonotactics and phonological parsing.
Jurafsky, Daniel - University of Colorado professor whose research includes machine learning, parsing and computational psycholinguistics. Current research, syllabi, and archive of publications in PostScript and PDF formats.
L2004 - Course module at UMIST providing a general introduction to the field, including parsing and sentence generation algorithms. In sequential HTML pages.
A Language of Metaphors - A theory that suggests that metaphors are based in mathematical truths, and may be key to both brain structure and artificial intelligence.
Learning Computational Grammars - A European research project which ran from 1998 to 2001, exploring the possibility of expanding computational grammars through machine learning. Publications, demos, project information.
Morphological Parsing - Downloads and documentation for the PC-KIMMO morphological parser, as well as background information and research in computational morphology.
Nordic Computational Linguistics Network - Serves the computational linguistics research communities in the Nordic and Baltic languages. Current activity in the field, past proceedings of the Nordic Computational Linguistics conferences, and comprehensive links. In Swedish and English.
Rieger, Burghard Publications - A list of papers in computational semiotics and computational semantics. Many are downloadable in PDF format.
SIGdial: Special Interest Group in Discourse and Dialogue - A subgroup of the Association for Computational Linguistics which supports empirical, standardized research in the computational analysis of spoken discourse, including standard corpora. Organizational information, events, and resources.
SIGGEN: Special Interest Group in Text Generation - A subgroup of the Association for Computation Linguistics, supporting research in computer generation of natural language. Organizational information and extensive natural language generation resources.
Speech Prosody at Bell Labs - Current research on non-lexical aspects of speech and paralinguistic communication. General information, downloadable papers, and multilingual text-to-speech demo.
Statistical Natural Language Processing - A web-based course in statistical natural language processing from Göteborg University, Sweden. Includes a basic reading course, set of student projects and inventory of useful resources.
WordNet Bibliography - A comprehensive list of research publications involving the WordNet lexical database.
The Xtag Project - Aims to develop a wide-coverage grammar of the English language, using a lexicalized tree adjoining grammar formalism. The current version of Xtag, as well as general resources for tree adjoining grammars.
Help build the largest human-edited
directory on the web.
