Yamli brings accurate, comprehensive Arabic query expander and indexer for your enterprise.
We are happy to announce the Yamli Arabic Query Expander, first of our many offerings to enterprises. The new service solves fundamental problems in search and data normalization, by smartly identifying all the English and Arabic script variations of an Arabic word.
Imagine that a simple name like “Mohamed Mansour” has at least 80 ways of spelling it, “Mohamed Saleh Abdallah” on the other hand has 7000 variations, “Jumeirah” the street in Dubai has at least 51 spellings, and the song “Habibi Ya Nor El Ein “can be spelled in 1207 variations.
Applications like banking, identity management, address management, media management and others can make use of the Yamli Query Expander today. The expander simply plugs in and works directly with existing database and search engine set up. This technology uses Yamli’s powerful algorithms coupled with the collected intelligence ensuring a very comprehensive coverage.
Among its features the Yamli Arabic Query Expander offers:
- Expansion of a query into all its Arabic and English variations. For example عبد الله , عبدالله, Aballah, Abdullah, Abdalla etc … This could be applied to people/place names and media content but to also any generic Arabic word.
- Frequency and ranking bias with each expanded result.
- Data cleansing and deduplication, to eliminiate duplicate entries and make sure the databases are in sync.
If you are interested in testing or if you would like to be a reseller of the technology contact us at team@yamli.com, in the meantime enjoy the funny video below 
Experimenting with a new approach to translation …
Ma
chine translation is a very tough problem and many have been doing a great job at improving its accuracy like Google, Babelfish and Sakhr. While we realize these tools solve a major problem, they don’t tackle one important piece: the flexibility to perfect the translated text. Perhaps it’s because they assume that users translate text for the purpose of reading it rather then actually using it for a blog post, email, document etc …
A couple of weeks ago we asked you how often you use translation tools and how you use them. We listened to your answers and decided to hack a quick translation tool as an experiment in finding a more natural interaction. We used Google’s translation API on the back end, while we focused on providing a free flowing end-user experience to allow them to perfect the translated text and easily move between the input and output.
This is still in the experimental stage so you might find a bunch of bugs but we would love to hear your feedback and find out whether you think we are moving in the right direction. Give it a try at www.yamli.com/translate/
Tags: translation
