Balie 1.5

Compliance with Java 1.5 and code improvements:

- Generalization of NER module (lower accuracy but greater scalability)

- Lot of token features now available: word-level (casing, numeric, single char), morphology, functional features from litterature. etc.

- Code beautification, maintenance, etc.

Enjoy!

Balie now available as a UIMA annotator

It is now possible to use Balie inside the IBM's UIMA framework (Unstructured Information Management Architecture). Balie named-entity capability can therefore be used as an annotator in a standalone product or in a pipeline of a more complex operation.

Note that the Balie+UIMA code is only available through the SourceForge CVS.

UIMA framework allows an information processing software to be put in the middle of a powerful and flexible service environment. UIMA manages input (e.g.: batch processing), parallel or distributed execution, logging, communication with other modules and delivery (e.g.: web service).

Here's a screen shot of Balie working inside UIMA (note that the GUI is provided by UIMA framework):

NLP Bot

Balie technology is used to power the world first NLP-capable robot that autonomously maintain a blog. The blog, located at http://gentilrobot.blogspot.com/, is updated without human intervention.

The robot first choose a topic in the scientific news.
It then analyse hundreds of related web pages using the Balie technology.
Then, it extracts "strong" opinions and also detect a range of sentiments like humor and anger.
It finally glu the best sentences using some coherence analysis and add some "random thought".
p.s.: The "random thought" module is powered by cutting-edge technology from the '70 NLP era.. (hard-coded sentences :p)

Balie 1.18

Balie 1.18 released today.

Lot of bug fixes.. speed improvements.. but nothing major.

CAUTION: the main "Tokenizer" call has one more parameter (boolean: flag the pos tagger ON-OFF).. It is not backward compatible..

Balie 1.17

Balie 1.17 is a snapshot of Balie before some major changes that will compose the 1.2 version. Changes in tokenization are expected (to handle various standards in literature). Changes in part-of-speech tagging are expected, as external product should be gradually removed.

Balie 1.16 now ready

This release contains no new features but many bug fixes. As of today, Balie successfully ran through millions of douments, a proof of speed and stability.

Balie Welcomes a new Developper!

We are happy to welcome Divan_Roulant, an experienced Java developper.
Divan_Roulant will work on morphology (e.g.: flexion suffixes) as well as maintenance and bug fixes on the core modules of Balie.