Gracias por tu visita. Esta página solo está disponible en inglés.
Alexa Blogs

Alexa Blogs

Want the latest?

alexa topics

Recent Posts

Archive

Showing posts tagged with Alexa science

August 13, 2019

Chieh-Chi Kao

Two new papers explore techniques for increasing the computational efficiency and reducing the memory footprints of neural networks that process audio data.

[Read More]

August 08, 2019

Mengwen Liu

Pooling the training data for related skills, and using it to train the skills simultaneously, improves performance for all of them.

[Read More]

August 07, 2019

Chetan Naik

Different Alexa services use different names for the same types of data, which makes it hard to track references across dialogues. By learning correlations between data types, a machine learning model can make better decisions about which references to track from one round of dialogue to the next.

[Read More]

July 31, 2019

Abdalghani Abujabal

Most question-answering systems rely on either text search or knowledge graphs. A hybrid approach, which knits together data from multiple textual sources to produce an ad hoc knowledge graph, yields better results on complex questions.

[Read More]

July 29, 2019

Larry Hardesty

The new focus areas for the Amazon Research Awards, which provide up to $80,000 in funding and up to $20,000 in Amazon Web Services Promotional Credits to academic researchers investigating topics related to machine learning, were announced this month. The application period opens on September 10.

[Read More]

July 22, 2019

Kai Hui

Treating news headlines and Wikipedia section headers as "search terms" and the associated texts as search results enables the training of neural search engines with less need for manually annotated data.

[Read More]

June 27, 2019

Larry Hardesty

Student system demonstrates how "early exit" strategies could improve Alexa's efficiency, by letting neural networks break off computations when they have high confidence in their solutions.

[Read More]

June 25, 2019

Jinseok Nam

Alexa scientists use machine learning to improve the performance of "multilabel classifiers", which classify data according to several categories at once — identifying multiple objects in an image, for instance, or multiple topics touched on by a single article.

[Read More]

June 13, 2019

Stan Peshterliev

New approach to "active learning", or automatically selecting training examples for machine learning, improves the performance of natural-language-understanding system by 7% to 9%.

[Read More]

June 11, 2019

Young-Bum Kim

Natural-language-understanding system that includes both a generic model for a language and several locale-specific models improves accuracy by an average of 59% over individual locale-specific models.

[Read More]

June 06, 2019

Arpit Gupta

A new Alexa system adopts a simpler, more scalable solution to the problem of "reference resolution", or tracking references through several rounds of dialogue, by overwriting referring words with their referents.

[Read More]

June 05, 2019

Alexa Science Team

At Amazon's re:MARS conference, Alexa VP and head scientist Rohit Prasad announced new AI technology that will enable Alexa to engage in multiturn dialogs that span skills, shifting the cognitive burden of complex task coordination from the customer to Alexa.

[Read More]

May 21, 2019

Viktor Rozgic

The combination of an autoencoder, which is trained to output the same data it takes as input, and adversarial training, which pits two neural networks against each other, confers modest performance gains but opens the door to extensive training with unannotated data. 

[Read More]

May 16, 2019

Ming Sun

Text normalization is the process of converting particular words of a sentence into a standard format so that software can handle them. Breaking inputs into component parts and factoring in syntactic information reduces the error rate of a neural text normalization system by 98%.

[Read More]

May 13, 2019

Judith Gaspers

Cross-lingual transfer learning improves performance of named-entity recognizer by up to 7.4% versus a system trained from scratch in the new language.

[Read More]

Want the latest?

alexa topics

Recent Posts

Archive