Amazon Developer Blogs

Amazon Developer Blogs

Showing posts tagged with Alexa Science

January 15, 2019

Anish Acharya

By compressing the huge lookup tables that list "embeddings", or vector representations of individual words, a new system can shrink neural-network models by up to 90%, with minimal effect on accuracy.

[Read More]

December 21, 2018

Rasool Fakoor

Personal memory retrieval systems are usually trained to do one thing then judged on their ability to do something else. Alexa scientists show how reinforcement learning lets them use the same criterion (F1 score) to both train and evaluate such systems.

[Read More]

December 18, 2018

Sanchit Agarwal

A new parser that learns which words of an utterance belong together enables Alexa to handle multistep requests.

[Read More]

December 17, 2018

Young-Bum Kim

Data representation schemes — such as "embeddings" — are a hot topic in machine learning. At this year's IEEE Spoken Language Technologies conference, Alexa scientists present a new representation scheme that cuts skill selection error rate by 40%.

[Read More]

December 13, 2018

Ankur Gandhe

New Alexa capabilities are often bootstrapped using "grammars", formal rules that can generate artificial training examples for machine learning systems. A new method for constructing statistical language models directly from grammars can improve speech recognition on new capabilities by up to 15%.

[Read More]

December 11, 2018

Chengwei Su

A new technique that lets different natural-language-understanding modules independently calibrate their judgments about whether they should handle a given utterance helps improvements reach Alexa customers more efficiently.

[Read More]

December 07, 2018

Ruhi Sarikaya

In an invited talk at the second NeurIPS workshop on Conversational AI today, Alexa scientist Ruhi Sarikaya will focus on the role of context in redefining human-computer interaction through natural language.

[Read More]

December 04, 2018

Behnam Hedayatnia

The addition of information about the last few turns of conversation and a small set of standard "dialogue act" tags boost Alexa's ability to determine the topic of an utterance by 35%.

[Read More]

November 19, 2018

Trevor Wood

Alexa researchers show that their new neural-network-based text-to-speech system can learn how to read news in the style of a TV newscaster from just a few hours of training data.

[Read More]

October 31, 2018

Young-Bum Kim

Amazon researcher Young-Bum Kim describes some new modifications to the machine learning model that selects the one skill out of thousands best suited to a particular customer request.

[Read More]