Simple grammatical mistakes or a slightly different word order doesn’t affect our thinking process. What is this distance between documents? Humans can quickly know which document is the most appropriate for this query, because language is inherent to us and we understand the meaning of each word and and also the sentence as a whole, we can even predict what each document is about. Document 5: ‘Data science is the top career in the 21st century’įirst we compute the distance between the query and the 5 documents, and the one(s) with the highest similarity are returned to the user.Document 4: ‘Data about chimpanzees is the basis of behavioral science’.Document 3: ‘ A marine biologist’s guide to getting a data science job’.Document 2: ‘Data science breakthroughs in 2019’.Document 1: ‘The science of cooking: how to cook a splendid meal’.Query: ‘ how do I start a career in data science?’.When the similarities are obtained, the documents are ranked accordingly and the ones at the top are retrieved.įor example, imagine that the ontology has 5 documents: In order to get the top most similar documents, the algorithm computes the distance between the query and many documents. The way semantic search engines retrieve results from their ontology is by computing the closest / most similar documents to the query. This one is about the Earth mover’s distance, which can be applied in semantic search. ![]() This is the part 2 of my initial Semantic search post.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |