US 12,236,204 B2
Slot filling using a zero shot model for conversational AI systems and applications
Shubhadeep Das, Kolkata (IN); Yi-Hui Lee, Dallas, TX (US); Oluwatobi Olabiyi, Falls Church, VA (US); and Zhilin Wang, Seattle, WA (US)
Assigned to NVIDIA CORPORATION, Santa Clara, CA (US)
Filed by NVIDIA CORPORATION, Santa Clara, CA (US)
Filed on Dec. 2, 2022, as Appl. No. 18/074,394.
Prior Publication US 2024/0185000 A1, Jun. 6, 2024
Int. Cl. G06F 40/56 (2020.01); G06F 40/284 (2020.01)
CPC G06F 40/56 (2020.01) [G06F 40/284 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a natural language input from a user;
identifying a mention span included in the natural language input; and
determining, using a machine learning model, that the mention span is associated with a slot class included in a set of slot classes based at least on a set of slot class descriptions corresponding to the set of slot classes.
 
10. The method of claim 1, wherein the machine learning model is trained using a set of training data that does not include at least one of the slot class or the mention span.