C++ STL with UTF-8

Portable Library
http://utfcpp.sourceforge.net/
https://sourceforge.net/projects/utfcpp

Conversion Tool
http://www.gnu.org/software/libiconv/

Articles
http://www.codeproject.com/KB/stl/upgradingstlappstounicode.aspx
http://www.codeproject.com/KB/stl/utf8facet.aspx
http://www.cplusplus.com/forum/beginner/7233/

--
Cheers,
Vu

GeoWordNet

http://geowordnet.semanticmatching.org/

NLP Tools (links from Caroline Sporleder)

http://www.coli.uni-saarland.de/~csporled/page.php?id=tools

Summarizing contents across websites in the Internet

Summarizing contents across websites in the Internet:

http://www.iresearch-reporter.com/
http://ultimate-research-assistant.com/

The summary quality of the above systems is not actually good (i think). One possible improvement is to focus mainly on summarizing contents from research papers which contain very useful and detailed technical materials. It could be regarded to "Related Work Summarization" (see my paper at here).

--
Cheers,
Vu

Vietnamese Language Processing

http://vlsp.vietlp.org:8080/demo/?page=home

It's amazing! But I've not checked their quality yet. Will do ASAP.

RandLM - the randomised language modelling toolkit

Link: http://sourceforge.net/projects/randlm/

Reference:
1) David Talbot and Miles Osborne. Smoothed Bloom filter language models: Tera-Scale LMs on the Cheap. EMNLP, Prague, Czech Republic 2007.
2) David Talbot and Miles Osborne. Randomised Language Modelling for Statistical Machine Translation. ACL, Prague, Czech Republic 2007.

NLP with Python

Book: http://www.nltk.org/book
Toolkit: http://code.google.com/p/nltk/