Amazon Technologies, Inc.

Shang-Wen Daniel Li

Yi Zhang

Roger Scott Jenke

Meghana Puvvadi

Rama Krishna Sandeep Pokkunuri

Peng Zhang

Jason Krone

Kartik Natarajan

Trevor Andrew Morse

Niranjhana Nayar

Garima Lalwani

Yi-An Lai

Techniques for updating a machine learning model based on user interactions are described. In particular, in some examples, user interactions with a chatbot provide aspects of a data set to be used to train or fine-tune a ML model. In some examples, this is accomplished by collecting data from a first plurality of interactions with a machine learning (ML) model; generating a variant of the ML model using the collected data by: filtering the collected data to create a first data set, training the ML model based on the first data set to generate an adapted ML model, and fine-tuning the adapted ML model on a second data set, different than the first data set to generate the variant of the ML model.

Adaptations of task-oriented agents using user interactions

Techniques for creating and calibrating natural-language understanding (NLU) machine learning models are described. In certain embodiments, a training service tunes parameters of a function, taking the output from an NLU machine learning model as an input of the function, to calibrate the NLU machine learning model's output to optimize the interpretability of the resulting output, e.g., confidence score(s). Embodiments herein include generating, by the NLU machine learning model, an output based at least in part on an input (e.g., utterance) from a user, and applying a tuned, output modifying function to the output from the NLU machine learning model to generate a modified output. An inference may be generated based at least in part on the modified output.

Confidence calibration for natural-language understanding models that provides optimal interpretability

Growing community of inventors

Somerville, MA, United States of America

Shang-Wen Daniel Li