Amazon Developer Blogs

Amazon Developer Blogs

Showing posts tagged with Alexa research

August 15, 2019

Boya Yu

Based on embeddings, system suggests named entities — or "slot values" — that developers might want their skills to recognize.

[Read More]

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 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]