Google searches huge swaths of data from a variety of sources - the entire web, their famed knowledge graph, and their comprehensive map of the world - in order to provide users the exact answers they’re looking for. There isn't a one-size-fits-all approach that will work for all these types of data. Instead, Google uses different algorithms, all powered by AI and deep learning, to search different data types. Yext Answers takes the exact same approach. See how our results compare to a search on Google:
There isn’t a single perfect search algorithm—that’s why Answers has multiple. Rather than keyword-based search, Answers uses a multi-algorithm approach to surface the best results, similar to how the top consumer search engines work.
Answers uses Named Entity Recognition—based on Google's open source machine learning framework BERT—to detect potential filters and show structured results from a Knowledge Graph. This works great for structured entities like products, events, and jobs.Learn More
FAQ data is more loosely structured than location or product data, but it contains rich information. Answers uses Semantic Text Search for FAQs. Instead of relying on keywords, we embed both search queries and FAQs in vector space and use an algorithm to determine the most relevant FAQs—no synonyms required!Learn More
Yext Answers is able to search unstructured data to identify the most relevant documents and answers. With Extractive QA, you can search through unstructured content like blog posts, help articles, and product manuals and extract relevant snippets that answer the query posed.Learn More