Amazon Technologies, Inc.

Mona Diab

Peng Zhang

Rashmi Gangadharaiah

Hassan Sawaf

Katrin Kirchhoff

Roger Scott Jenke

Kalpesh N Sutaria

Arshit Gupta

Garima Lalwani

Adel A Youssef

Techniques are described for a contextual natural language understanding (cNLU) framework that is able to incorporate contextual signals of variable history length to perform joint intent classification (IC) and slot labeling (SL) tasks. A user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent is received. The user utterance and contextual information associated with one or more previous turns of the multi-turn chat dialog is provided to a machine learning (ML) model. An intent classification and one or more slot labels for the user utterance are then obtained from the ML model. The cNLU framework described herein thus uses, in addition to a current utterance itself, various contextual signals as input to a model to generate IC and SL predictions for each utterance of a multi-turn chat dialog.

Contextual natural language understanding for conversational agents

Growing community of inventors

Seattle, WA, United States of America

Mona Diab