Amazon Technologies, Inc.

Arshit Gupta

Yi Zhang

Peng Zhang

Katrin Kirchhoff

Roger Scott Jenke

Hassan Sawaf

Rashmi Gangadharaiah

Harshal Pimpalkhute

Kalpesh N Sutaria

Garima Lalwani

Subhojit Das

Julian E S Salazar

Elman Mansimov

Sebastien Jean

Aditi Tripathi

Mona Diab

Sandeep Srinivasan

Adel A Youssef

Sudip Dutta

Chengshun Zhang

A natural language processing system may implement one or more composite slot types. The natural language processing system may receive a request to create a composite parameter type for causing performance by the natural language processing system of an intended action. The natural language processing system determines based on the request, a plurality of sub-parameters of the composite parameter type and generates a Boolean expression that relates two or more sub-parameters. The natural language processing system may apply the composite parameter type to determine that the pluralities of sub-parameters in an input text satisfies the Boolean expression to initiate performance of the intended action.

Composite slot type for natural language processing

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

A spoken language understanding (SLU) system may include an automatic speech recognizer (ASR), an audio feature extractor, an optional synchronizer and a language understanding module. The ASR may produce a first set of input data representing transcripts of utterances. The audio feature extractor may produce a second set of input data representing audio features of the utterances, in particular, non-transcript specific characteristics of the speaker in one or more portions the utterances. The two sets of input data may be provided for the language understanding module to predict intents and slot labels for the utterances. The SLU system may use the optional synchronizer to align the two sets of input data before providing them to the language understanding module.

Multi-modal spoken language understanding systems

Growing community of inventors

Seattle, WA, United States of America

Arshit Gupta