#bbuzz: Natural Language Search at Salesforce
Formal Metadata
| Title | #bbuzz: Natural Language Search at Salesforce |
|
| Title of Series | |
| Number of Parts | 48 |
| Author | |
| Contributors | |
| License | You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. |
| Identifiers | |
| Publisher | |
| Release Date | |
| Language | |
Content Metadata
| Subject Area | |
| Genre | |
| Abstract | Natural language is hard when your target is not a single organization, but the tremendous number of Salesforce customers, each with their own unique customization.
In this privacy-first world that Salesforce always operated in, it is even harder to do without having access to customer data to train machine learning models.
In this talk, we will describe how we implemented, deployed and nurtured Salesforce flavour of Natural language queries. Our approach is a battle-tested mix of deep-learning, solr search indexes, and basic engineering techniques.
This talk is presented by SalesForce. |
|
