Stockholm, Sweden

Gavagai on Twitter Gavagai on LinkedIn

In their own words

Gavagai has developed Ethersource, the most powerful and versatile semantic engine in commercial or military use today. The performance of Ethersource is unrivaled with respect to six crucial features:

Multilinguality. Ethersource can handle any language (and by extension all sequential symbol systems).

Scalability. Ethersource provides realistic scale coverage and real-time analysis of human language information streams of any size.

Meaning. Ethersource will outperform ALL other models in recognized semantic benchmark tests (we are happy to prove this in a public challenge). The base model which is based on decades of scientific research and hundreds of academic publications is, for instance, widely known to produce state-of-the-art results on the TOEFL synonym test.

Learning. Ethersource models meaning as it emanates from current actual language use; it neither presumes nor relies on external resources. Language is in a constant state of flux, and so is Ethersource.

Completeness. In contrast to most systems, Ethersource is not based on sampling, and does not dependent on external lists of terms or concepts. Ethersource reads EVERYTHING and can be used to model anything that has been mentioned, without retraining.

Robustness. Ethersource presumes that "language is in order as it is", and is designed to cope and thrive with variability, noise, and inconsistencies. Real language data is not lean, clean, and neat. Text with new conventions, misspellings, non-standard usage, and code switching poses new challenges for text processing tools. Any model that presumes stability, order, and consistency will break down when exposed to actual language use.

Gavagai in SMA news

Profile updated 16 April 2014