Lingo4G and Lingo3G are independent and complementary products.
See the table below or contact us for some help choosing which one is best for you.
|Primary use case||Processing of collections available in advance for indexing before clustering.||Processing of small and medium collections of ad-hoc content, such as search results.|
|Maximum input collection size||
Millions of documents
Thousands of documents
Stateful. Lingo4G first needs to index all your documents and only then can it analyze the whole indexed collection of a subset of it. Including previously unseen documents in an analysis requires re-indexing.
The split into two phases allows Lingo4G to perform the expensive operations, such as tokenization of documents, only once during indexing.
Stateless. Lingo3G performs processing in one step, all documents provided on input will be immediately processed and disposed of.
The stateless paradigm makes it possible to process arbitrary and previously unseen documents. The cost is that the time-consuming operations, such as tokenization, will be repeated for each set of documents being processed.
See Lingo4G manual for more differences between Lingo4G and Lingo3G.
Stephan Schmid, CEO at Comcepta, Switzerland
Dr James Thomas, Associate Director, EPPI-Centre, Social Science Research Unit, Institute of Education, London
René de Vries, Managing Director at HowardsHome