Details
| Original language | English |
|---|---|
| Patent number | US20190188317A1 |
| IPC | G06F17/30684,G06F16/3344,G06N20/00,G06N99/005 |
| Priority date | 15 Dec 2017 |
| Filing date | 15 Dec 2017 |
| Publication status | Published - 20 Jun 2019 |
Abstract
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Patent No.: US20190188317A1. Jun 20, 2019.
Research output: Patent
}
TY - PAT
T1 - Automatic seeding of an application programming interface (api) into a conversational interface
AU - Kashyap, Sujatha
AU - Rellermeyer, Jan Simon
AU - Rozner, Eric
AU - Schaub, Jeremy D.
PY - 2019/6/20
Y1 - 2019/6/20
N2 - Systems, methods, and computer-readable media for automatically seeding an API into a natural language conversational interface are described herein. An API is automatically seeded into a natural language conversational interface by mapping a set of API calls to a set of intents, mapping the set of intents to a collection of example utterances, and using the collection of example utterances as input training data to train a natural language classifier. The trained classifier may then be used to determine an intent associated with a received query such that an action associated with the determined intent can then be performed.
AB - Systems, methods, and computer-readable media for automatically seeding an API into a natural language conversational interface are described herein. An API is automatically seeded into a natural language conversational interface by mapping a set of API calls to a set of intents, mapping the set of intents to a collection of example utterances, and using the collection of example utterances as input training data to train a natural language classifier. The trained classifier may then be used to determine an intent associated with a received query such that an action associated with the determined intent can then be performed.
M3 - Patent
M1 - US20190188317A1
Y2 - 2017/12/15
ER -