Dive into NLP with the Elastic Stack
Lucian Precup and Pietro Mele • Location: Theater 5 • Back to Haystack 2023
Natural language processing has been changing radically since the advent of deep learning and new language models. How can we practically use these tools in our products, especially when we are more of a developer than a Data Scientist? We will see that we can already use many of the features brought by these models directly in Elasticsearch and its suite:
- Semantic vectorization "on the fly" (via Ingest Pipeline)
- Semantic search (semantic vector-based)
- Named Entities Recognition
- Multimodal search (e.g. retrieve images from text query)
- Automatic classification
We will quickly introduce these concepts and their practical applications. We’ll show that we do not necessarily need to revolutionize the technical stack to interact more naturally with our users.Download the Slides Watch the Video
Lucian Precup is the CTO of all.site - the collaborative search engine developed at Station F in Paris. With his colleagues at Adelean, Lucian develops solutions for indexing, searching and analyzing data. Lucian regularly shares his knowledge in specialized conferences and organizes the Paris Search & Data Meetup.
Pietro is a highly motivated software engineer with a focus on developing cutting-edge search engine solutions. With experience at both Adelean and the INA (French media institution responsible for preserving and promoting French audio-visual heritage), he has honed his expertise in using Elasticsearch to deliver efficient and effective results. He has a strong background in machine learning and computer vision and he is continuously learning and expanding his skillset. Outside of work, he enjoys reading, sports, and coding for fun.