Query expansion

As part of a search engine for institutional documents, I designed and developed a fast pipeline for the interpretation and expansion of the user query. In the query, named entities, dates, domain terms and complex terms are detected. Common terms are enriched with their most inherent synonyms, estimated on the basis of context: I conceived a simple Word sense disambiguation algorithm, which combines knowledge from Wordnet and word embeddings. The pipeline simplifies and makes the search on the site more effective, concretely increasing transparency.

Used by: Municipality of Milan, Municipality of Palermo, Region of Umbria, Region of Sicily…