Cross-Lingual Search Based on Concepts and Meaning

Cross-lingual semantic search using text embeddings

We’ve recently released this whitepaper which explores a new way to solve cross-lingual semantic search. Rather than use machine translation to translate queries or search records, this approach delivers better accuracy based on semantics, not translation. Semantic search (aka, concept search) goes beyond finding keywords, to retrieving ideas suggested by the keywords.

In part 1 we will compare the traditional translation-based approach with a newer approach using text embeddings — a natural language processing technology that encodes the meaning of words as mathematical vectors.

In part 2 we will look at implementing semantic search via:

  • How to retrofit an existing keyword search engine to add cross-lingual and fuzzy search
  • Ways to overcome issues of speed and searching very large data sets
  • A specific use case: targeted topic and event extraction
  • The special case of cross-lingual name matching

Download the whitepaper now