Computational Linguistics/NLP links

Paper Archives and Logs

• ACL Anthology: A Digital Archive of Research Papers in Computational Linguistics
• MT archive: Electronic repository and bibliography on machine translation
• Language Log

Overview sites

• NLP
  • Speech and Language Web Resources
  • List of selected NLP papers and some resources
• Information Retrieval
  • Kenji Kita collection
• Latent Semantic Analysis
  • University of Colorado, Boulder
  • Readings in Latent Semantic Analysis for Cognitive Science and Education
  • Infomap NLP Software: An Open-Source Package for Natural Language Processing. Uses a variant of Latent Semantic Analysis (LSA), indexes documents, and can perform information retrieval and word-word semantic similarity computations.
  • Get LSA tools from Telcordia
  • SVDPACK: Package comprises 4 numerical (iterative) methods for computing the singular value decomposition (SVD) of large sparse matrices
• Text Summarization
  • Dragomir Radev's supported page
• Perl for Linguistics
  • What are the monks doing with Perl and Linguistics?

Terminology

• Glossary of linguistic terms

Tools

• List of tools for dictionary research and development
• Simple Concordance Program: Create word lists and search natural language text files for words, phrases, and patterns. Has built-in alphabets for English, French, German, Greek, Russian, etc.
• TouchGraph: Browsing CiteSeer, by exploring links between related articles
• VisualText: VisualText is an Integrated Development Environment for deep text analysis applications. Think of it as Visual C++ for Natural Language Processing applications.
• NLTK: Natural Language Toolkit
• CLUTO: a clustering package for high-dimensional datasets.
• Minipar: a dependency parser for English
• FreeLing: library providing language analysis services (such as morfological analysis, date recognition, PoS tagging, etc.)
• Agrep: a tool for fast searching a file or many files for a string or regular expression, with approximate matching capabilities and user-definable records
• SVMTool: a simple and effective part-of-speech tagger based on Support Vector Machines
• WordSmith: a lexical analysis software for the PC
• Simple text tools: Text Statistics, Lemmatizations, and Concordances

Resources

• Stanford Annotated List of Linguistic Resources
• Text Categorization Test Collections
• US legal texts
  • HTML version
  • XML version
  • Disorganized colophon muttering about various technical aspects of the project
• The Linguist's Search Engine

Bioinformatics

• BioNLP Resources (by Alex Morgan)
• Bioperl.org project
• Sequence comparison tools
• Gene's Now
• Ontologies
• Proteinhalt i text (Yapex Gene tagger)
• PRIME
• GENA
• Links to the Genetic World

Information Retrieval

• Web Term Document Frequency and Rank

Document Clustering

• System of Hypermatrix Analysis, Retrieval, Evaluation and Summarisation

Finite State Machines

• Finite state utilities
• Finite State Morphology - The Book
• AT&T toolkit

Corpora

• MuchMore Springer Bilingual Corpus

Other Languages

• Brill's tagger for New Norwegian (nynorsk)

Slavic Linguistics

• Bulgarian Linguistic Links
• SLAVLING: Slavic Linguistics Society
• SEELANGS: The Slavic and East European Languages and Literature List

People

• LINGUIST's Directory of Linguists
• REPTIL

Mail Lists

• LINGUIST
• CORPORA
• LEXICOGRAPHY
• SLAVLING: Slavic Linguistics Society
• SEELANGS: The Slavic and East European Languages and Literature List

Plagiarism detection

• METER: detecting and measuring text reuse in the domain of journalism
• CNN: New software detects plagiarized passages

Random stuff

• Mixture Modelling page
• Unicode editor Yudit

Finally... Some FUN!!!

• Google Fight
• Networking and Diversity (Bulgarian body language interpretation problems, The FreeBSD Developers' Handbook prospective)
• Why I Will Never Have A Girlfriend by Tristan Miller