Antelope stands for Advanced Natural Language Object-oriented Processing Environment. This framework facilitates the development of Natural Language Processing software. Antelope, currently in (beta) version 0.8.7, is designed for the Microsoft .NET framework (version 2.0 or above). Therefore, you can use it with C#, Visual Basic.NET, Delphi.NET and many other .NET compliant languages (even COBOL.NET!).

Please click here to download Antelope (you must be registered).

Antelope was tested under Windows XP, Vista 32 bits and Vista 64 bits (in x86 mode). Antelope includes the following features:

• Multi-threading support (experimental), can be used on a Web server,
• All-new, ribbon-based, Graphical User Interface,
• Access to many part-of-speech taggers, including the SS Tagger,
• A chunker with "divide & conquer" strategies,
• Access to the Link Grammar dependency parser,
• Access to the Stanford Parser 1.6 (no need of a Java VM),
• A parser for the French language,
• A full lexicon, with rich relations, based on WordNet 3.0 data,
• A very versatile user-defined lexicon facility,
• A "French WordNet",
• A 300,000 synsets extension with a mapping to Wikipedia,
• A syntax / semantic layer, based on VerbNet 1.5 (experimental),
• An anaphora resolver (experimental),
• A space and time features detector (experimental),
• A collocation collapser,
• A sentence splitter for plain text or HTML text,
• A PROLOG interpreter for .NET,
• A Context Extraction module,
• Deep syntax extraction,
• Paraphrases extraction (very experimental),
• A syntactic Web search utility,
• Documentation with samples in both C# and Visual Basic.NET.

(Copyright - Third party programs and data are property of their respective owners.)

The middle-term objective of Antelope (version 1.0, expected in early-2010) is to offer a true, easy to use, semantic parser. It will be first applied on an encyclopedia (a large subset of Wikipedia seems to be a nice target) to make complex queries possible at a semantic level.

Only English is fully supported for the moment, since English has many available linguistic resources. We have started supporting French (with the TagParser), and other European languages will be supported in 2009.