app card
Semantic In-Domain Product Identification for Search Queries
Sharma, Sanat, Kumar, Jayant, Naik, Twisha, Lu, Zhaoyu, Srikantan, Arvind, King, Tracy Holloway
Accurate explicit and implicit product identification in search queries is critical for enhancing user experiences, especially at a company like Adobe which has over 50 products and covers queries across hundreds of tools. In this work, we present a novel approach to training a product classifier from user behavioral data. Our semantic model led to >25% relative improvement in CTR (click through rate) across the deployed surfaces; a >50% decrease in null rate; a 2x increase in the app cards surfaced, which helps drive product visibility.
Country:
- North America > United States > California > Santa Clara County > San Jose (0.06)
- North America > United States > District of Columbia > Washington (0.05)
Technology:
- Information Technology > Information Management > Search (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Text Processing (0.50)
- Information Technology > Artificial Intelligence > Natural Language > Information Retrieval (0.47)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.47)