gerpublishing.blogg.se

These vectors have been encoded by one of these special NLP models, called sentence transformers. Let’s dive into how Spotify built its natural language podcast search. As Spotify has proven, it can lead to a much greater user experience. They both describe being or eating healthier over the winter holidays.Įnabling meaningful search is not easy, but the impact can be huge if done well.

We could see much better results because semantic search looks at the meaning of the words and sentences, not specific terms.ĭespite sharing no words, our query and episode description would be identified as having very similar meanings. Suppose we were to swap that for a semantic search query. These episodes likely have nothing to do with our intended search query, but we could return them. To make matters worse, there are undoubtedly thousands of episode descriptions on Spotify containing the words “eat”, “better”, and “holidays”. We have zero overlaps between the query and episode description using term matching, so this result would not be returned using keyword search. Preeya Alexander about how to stay healthy over Christmas and about her letter to patients." Its description is: "Alex Straney chats to Dr. There is a podcast episode talking about precisely this. How would we search for that? It might look something like: Imagine we wanted to find a podcast talking about healthy eating over the holidays. It enables a more intuitive search experience because we tend to have an idea of what we’re looking for, but rarely do we know precisely which terms appear in what we want. This technology relies on what we like to call semantic search. Now, they can search in natural language, in much the same way we might ask a real person where to find something. In the past, users had to rely on keyword/term matching to find the podcast episodes they wanted. Spotify’s natural language search for podcasts is a fascinating use case.

From their all-in-one podcast creation app (Anchor) to podcast APIs and their latest natural language enabled podcast search. To back their podcast investments, Spotify has worked on making the podcast experience as seamless and accessible as possible. Despite only entering the game in 2018, by late 2021, Spotify had already usurped Apple, the long-reigning leader in podcasts, with more than 28M monthly podcast listeners In a few short years, they have become the undisputed leaders in podcasting. ĭriving the charge in podcast adoption is Spotify. The market for podcasts has grown tremendously in recent years, with the number of global listeners having increased by 20% annually in recent years. Want to add audio search to your applications just like Spotify? You’ll need a vector database like Pinecone. How Spotify Uses Semantic Search for Podcasts