About Adsotrans
Adso is an open source toolset for Chinese text analysis. With over 185,000 words and phrases, our backend dictionary is the largest open source Chinese-English dictionary available. Our accompanying software uses a combination of statistical and rules-based algorithms to analyse the grammatical and semantic structure of Chinese text, and provides enterprise-quality text analysis services for everything from text annotation and content extraction to search preprocessing and gist translation. Download the software and database here. Adso is:

  • Driven by Artificial Intelligence
    Adso is a semantic engine, not simply a dictionary-lookup tool. The software attempts to pick the most sensible gloss for any entry based on its grammatical and ontological content. It understands the difference between the words "Al Qaida" and "base", for instance, and catches subtle nuances in language usage as occur with duoyinci.

  • Extensible
    Adso is a flexible machine-analysis system. The software supports a special XML markup language which enables the complete customization of engine output.

  • Smart
    Adso automatically identifies many dates and times, and personal and geographic place names, prices, addresses and much more. The software also searches for foreign loanwords and provides an appropriate explanation rather than an inaccurate and broken gloss for these words.

Adso is proud to support the next generation of intelligent language software, including Justin Kovalchuk's Chinese Perakun Firefox plugin, and Chris Fong's excellent ZDT flashcard software. We also provide data free of charge to users of Mike Love's commercial Plecodict project. Feel free to contact us if we can help you.

If you share our goals, use our materials, and would like to help us in our mission, please consider helping us add missing content to our backend database. Data entry can be done either through Adsotrans itself, or through the contributing ChinesePod Dictionary. For legal reasons, contributors affirm that submissions have not been drawn from copyrighted sources and submit equal copyright over entries to the Adso project. All submissions are reviewed for accuracy and edited to maximize compatibility with Adso algorithms and part-of-speech markup standards.

Inquiries, comments and questions are always welcome: david.lancashire |at| gmail.com.