NLTK 2.0 (Natural Language Tooklt) is a free, open source collection of Python modules, linguistic data and documentation for research and development in natural language processing and text analytics, with distributions for Windows, Mac OS X and Linux. It offers a platform for building Python programs to work with human language data, and integrates a guide to programming fundamentals.

RiTa is a free, open-source natural language library for work with generative literature, offered as both a 'core' package of jar files and documentation, and a text-to-speech package. It is designed to be simple and intuitive while still offering flexibility to advanced users via statistical models for tagging, chunking and parsing. RiTa may also be integrated with Processing.

Stanford CoreNLP is a free Natural Language Processing tool. It processes English language text and provides the base forms of words, parts of speech, indicates whether they are proper names, normalizes dates, times and numeric quantities, and marks up the structure of sentences. This tool integrates all other Stanford NLP tools for English language processing, including parts-of-speech (POS), the named entitiy recognizer (NER), the parser and the coreference resolution system. An online demo is also available.

Stanford Named Entity Recognizer is a free Java implementation for the recognition of proper names and other nouns and a part of the Stanford Natural Language Processing toolset. It also includes person, location and organizational recognition. This tool can be used with English or German text.

Stanford Part-of-Speech Tagger is a free Java implementation for the recognition of parts of speech, and a part of the Stanford Natural Language Processing toolset. It reads text and assigns parts of speech to each word such as noun, verb or adjective. This tool can be used with English, French, Arabic and German text.

Stanford Parser is a free Java implementation for the statistical parsing of text, and a part of the Stanford Natural Language Processing toolset. This tool can be used with English, Chinese, German and Arabic. A demo web browser version is also available. 

Stanford Phrasal is a a free Java implementation for phrase-based machine translation. It provides an easy to use API for implementating new decoding model features and supports unique capabilities such as translating using phrases that include gaps and conditional extraction of phrase-tables and lexical reordering models. 

Stanford Tokenizer is a free Java implementation for diving an English text into tokens such as words, and a part of the Stanford Natural Language Processing toolset. This tool is not available on its own, but is bundled with other tools in the same set, including Stanford Parser, Stanford Part-of-Speech Tagger, Stanford Named Entity Recognizer, and Stanford CoreNLP.

Apache OpenNLP is a free, open source toolkit for processing natural language text, based on machine learning. It includes common natural language processing functions such as tokenization, sentence segmentation, part-of-speech tagging, named entity extraction, chunking, parsing, and coreference resolution.

SEASR's OpenNLP Entities to Protovis Network Graph is a free tool for extracting entities within a specified sentence distance within a text. The OpenNLP system is used for entity extraction, and their relationships are represented in a link node network graph generated in Protovis. 

While SEASR is still active, their page for OpenNLP Entities to Protivis Network Graph is no longer available. It can still be viewed via the Internet Archive.