{"id":166,"date":"2021-03-05T13:59:15","date_gmt":"2021-03-05T13:59:15","guid":{"rendered":"https:\/\/wordlift.io\/ng\/?p=166"},"modified":"2021-03-05T14:02:36","modified_gmt":"2021-03-05T14:02:36","slug":"semantic-search","status":"publish","type":"post","link":"https:\/\/wordlift.io\/ng\/semantic-search\/","title":{"rendered":"What is Semantic Search, and how does it work?"},"content":{"rendered":"\n

If you work in SEO, you have been reading about Google and Bing becoming semantic <\/em>search engines but, what does Semantic Search really mean<\/strong> for users, and how things work under the hood?<\/p>\n\n\n\n

Semantic Search <\/strong>helps you surface the most relevant results for your users based on search intent and not just keywords.<\/p><\/blockquote>\n\n\n\n

Semantic (or Neural) Search uses state of the art deep learning models to provide contextual and relevant results to user queries<\/strong>. When we use semantic search we can immediately understand the intent behind our customers and provide significantly improved search results that can drive deeper customer engagement. This can be essential in many different sectors but – here at WordLift – we are particularly interested in applying these technologies to: travel brands<\/em>, e-commerce<\/em> and online publishers<\/em>.  <\/p>\n\n\n\n

Information is often unstructured and available in different silos, using semantic search<\/strong> our goal is to use machine learning techniques<\/strong> to make sense of content and to create a context. When moving from syntax<\/em> (for example how often a term appears on a webpage) to semantics, we have to create a layer of metadata<\/strong> that can help machines grasp the concepts behind each word. Google defines this ability to connect words to concepts as “Neural Matching<\/strong>” or *super synonyms<\/em>* that help better match user queries with web content. Technically speaking this is achieved by using neural embeddings<\/strong> that transform words (or other types of content like images, video or audio clips) to fuzzier representations of the underlying concepts.<\/p>\n\n\n\n

As part of the R&D work that we’re doing, in the context of the EU-cofounded project called WordLift Next Generation<\/strong><\/a>, I have built the prototype using an emerging open-source framework called Jina AI<\/strong> and the beautiful photographic material<\/strong> published by Salzburgerland Tourismus<\/a> (also a partner in the Eurostars research project) and \u00d6sterreich Werbung<\/a> \ud83c\udde6\ud83c\uddf9 (Austrian National Tourist Office).<\/p>\n\n\n\n

\n