An end-to-end neural query understanding system that understands natural language queries.

Forged by firsthand experience

Unlike intact articles, queries in natural language often lack key information or grammar components, which sets substantial obstacles for programs to process. Peak Labs has been handling first-hand user queries for years, and has distilled the experience into Leliel, which now supports nearly every module in Magi project that deals with query inputs.

In-depth question analysis

Leliel is capable of extracting entity and predicate phrases from query strings, detecting latent intents, generating contextual embedding vectors of extracted phrases, etc. For better recall, Leliel can also expand the understanding of properties to their synonyms.

Products built upon Leliel

Also available in: 中文