Query Attribute Modeling: Improving search relevance with Semantic Search and Meta Data Filtering
This addresses search limitations for enterprise applications, particularly in e-commerce systems, by reducing noise and enabling focused retrieval, though it appears incremental as it builds on existing methods like semantic search and metadata filtering.
This study tackled the problem of improving search precision and relevance by introducing Query Attribute Modeling (QAM), a hybrid framework that decomposes open text queries into structured metadata tags and semantic elements, achieving a mean average precision at 5 (mAP@5) of 52.99% on the Amazon Toys Reviews dataset.
This study introduces Query Attribute Modeling (QAM), a hybrid framework that enhances search precision and relevance by decomposing open text queries into structured metadata tags and semantic elements. QAM addresses traditional search limitations by automatically extracting metadata filters from free-form text queries, reducing noise and enabling focused retrieval of relevant items. Experimental evaluation using the Amazon Toys Reviews dataset (10,000 unique items with 40,000+ reviews and detailed product attributes) demonstrated QAM's superior performance, achieving a mean average precision at 5 (mAP@5) of 52.99\%. This represents significant improvement over conventional methods, including BM25 keyword search, encoder-based semantic similarity search, cross-encoder re-ranking, and hybrid search combining BM25 and semantic results via Reciprocal Rank Fusion (RRF). The results establish QAM as a robust solution for Enterprise Search applications, particularly in e-commerce systems.