Large language models (LLMs) have come to dominate the field of natural-language processing, so it’s no surprise that they also dominate the research that ...

Transfer learning is the technique of adapting a machine learning model trained on abundant data to a new context in which training data is sparse.On the ...

Traditionally, Alexa has interpreted customer requests according to their intents and slots. If you say, “Alexa, play ‘What’s Going On?’ by Marvin Gaye,” ...

In the past year, we’ve introduced what we call name-free skill interaction for Alexa. In countries where the service has rolled out, a customer who wants ...

Recently, we published a paper showing that training a neural network to do language processing in English, then retraining it in German, drastically ...

Text normalization is an important process in conversational AI. If an Alexa customer says, “book me a table at 5:00 p.m.”, the automatic speech recognizer ...

Today, customer exchanges with Alexa are generally either one-shot requests, like “Alexa, what’s the weather?”, or interactions that require multiple ...

In order to engage customers in longer, more productive conversations, Alexa needs to solve the problem of reference resolution. If Alexa says, “‘Believer’ ...

As Alexa expands into new countries, she usually has to be trained on new languages. But sometimes, she has to be re-trained on languages she’s already ...

Alexa’s ability to respond to customer requests is largely the result of machine learning models trained on annotated data. The models are fed sample texts ...