» 20-Newsgroups

See full content »

Resource type:

Corpora

Description:

20000 messages taken from 20 Usenet newsgroups. Available for scientific use.

Resource link:

» AGFL

See full content »

Resource type:

NLP and IR Software

Description:

System for natural languagegrammar development and automatic generation of efficient analyzers for these grammars. Available for Windows and Unix. GNU GPL License.

Resource link:

» Apertium

See full content »

Resource type:

NLP and IR Software

Description:

Open source automatic Translator for Spanish state languages. For 32-bit MS Windows (95/98/NT/2000/XP), POSIX (Linux / BSD / Unix OSes). GPL License.

Resource link:

» Bayesian Logistic Regression Software

See full content »

Resource type:

Machine Learning y Data Mining Software

Description:

This software implements Bayesian Logistic Regression with two options: Gaussian and Laplace (also known as double exponential). Free for non-commercial use. Available for Windows and Linux

Resource link:

» Bayesian Multinomial Regression Software

See full content »

Resource type:

Machine Learning and Data Mining Software

Description:

This software implements Bayesian Multinomial Logistic Regression. Free for non-commercial use. Available for Windows and Linux

Resource link:

» BoosTexter

See full content »

Resource type:

Machine Learning and Data Mining Software

Description:

Text classifier based on boosting. It can handle: Multiple attributes that can be textual, discrete or continuous, data with missing attributes, multiclass problems and large clean sets of data. Free license for non-commercial use only.

Resource link:

» BOW

See full content »

Resource type:

NLP and IR Software

Description:

C library for modeling, Information Retrieval and Text Classification. For Unix and WindowsNT. LGPL License.

Resource link:

» CCG-NER

See full content »

Resource type:

NLP and IR Software

Description:

Entity Name Tagging. Package incorporating versions of SNoW (network classifiers) and FEX, together with a module inference. The result is a robust system with good performance on new data. Free license for academic and research use.

Resource link:

» Collins Parser

See full content »

Resource type:

NLP and IR Software

Description:

Natural language parser. GNU License

Resource link:

» Collins Parser

See full content »

Resource type:

NLP and IR Software

Description:

Natural language parser. GNU License

Resource link:

» CoolTran

See full content »

Resource type:

NLP and IR Software

Description:

Multiplatform terms translator in different languages. It has several preinstalled language dictionaries, but more can be installed, as well as a “collaborative” Internet database, to which the application connects. Implementation in Java. GPL License.

Resource link:

» Email SPAM ENRON Corpus

See full content »

Resource type:

Machine Learning and Data Mining Software

Description:

Spam filter with Naive Bayes

Related links:

» FIRE

See full content »

Resource type:

NLP and IR Software

Description:

Flexible Image Retrieval Engine. Given an image as a question, the goal is to find images in a database that are similar to the given image. GNU Public Licence

Resource link:

» FOIL

See full content »

Resource type:

Machine Learning and Data Mining Software

Description:

First Order Inductive Learner. Used to generate Rating Classification Association rules (CARs). Max three attributes in the antecedent of a rule

Resource link:

» Freeling

See full content »

Resource type:

NLP and IR Software

Description:

Library that provides services for the analysis of language. It can be used as an external library or through an interface that allows you to analyze files from the command line. Some features: text tokenization, sentence splitting, morphological analysis, detection and classification of entities, recognition of dates / numbers / money / proportions, PoS tagging, Chart-based shallow parsing, detecting physical parameters (speed, weight, temperature, density, etc.), sense annotation based on Wordnet. For Spanish, Catalan, Italian, Galician.

Resource link: