Retro Relevance: Lessons Learned Balancing Keyword and Semantic Search
Offered By: OpenSource Connections via YouTube
Course Description
Overview
Explore the challenges and limitations of semantic search in this conference talk from Haystack US 2024. Delve into scenarios where semantic search falls short, particularly with niche queries and domain-specific jargon. Learn how to bridge the gap between semantic search capabilities and user expectations by leveraging traditional search relevance building blocks. Discover strategies for implementing hybrid queries that combine BM25 keyword search with semantic search, utilizing tools such as query rules for contextual document pinning and synonyms for capturing domain-specific language. Gain practical insights on enhancing search relevance through a comprehensive approach that complements semantic search, ensuring improved performance and user satisfaction. Presented by Kathleen DeRusso, Principal Software Engineer at Elastic, this talk offers valuable lessons for developers and search professionals looking to optimize their search systems.
Syllabus
Haystack US 2024- Kathleen DeRusso:Retro Relevance:Lessons Learned Balancing Keyword&Semantic Search
Taught by
OpenSource Connections
Related Courses
SPLADE - The First Search Model to Beat BM25James Briggs via YouTube Supercharge eCommerce Search - OpenAI's CLIP, BM25, and Python
James Briggs via YouTube Vector-Based Methods for Similarity Search - TF-IDF, BM25, SBERT
James Briggs via YouTube RAG with Verified Citations - Advanced Inference Techniques
Trelis Research via YouTube Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers
Trelis Research via YouTube