Natural-language understanding (NLU)

Towards better confidence estimation for neural models

Vishal Thanvantri Vasudevan, Abhinav Sethy, Alireza Roshan-Ghias

ICASSP 2019

2019

In this work we focus on confidence modeling for neural network based text classification and sequence to sequence models in the context of Natural Language Understanding (NLU) tasks. For most applications, the confidence of a neural network model in it’s output is computed as a function of the posterior probability, determined via a softmax layer. In this work, we show that such scores can be poorly calibrated

Conversational AI

Innovations from the 2018 Alexa Prize

Behnam Hedayatnia

March 05, 2019

The 2018 Alexa Prize featured eight student teams from four countries, each of which adopted distinctive approaches to some of the central technical questions in conversational AI. We survey those approaches in a paper we released late last year, and the teams themselves go into even greater detail in the papers they submitted to the latest Alexa Prize Proceedings. Here, we touch on just a few of the teams’ innovations.

Conversational AI

Contextual Query Rewrite (CQR) Dataset for spoken dialogue

Pushpendre Rastogi, Arpit Gupta, Tongfei Chen, Lambert Mathias

2019

Dialogue assistants are used by millions of people today to fulfill a variety of tasks. Such assistants also serve as a digital marketplace where any developer can build a domain-specific, task-oriented, dialogue agent offering a service such as booking cabs, ordering food, listening to music, shopping etc. Also, these agents may interact with each other, when completing a task on behalf of the user. Accomplishing

Conversational AI

AI tools let Alexa Prize participants focus on science

Anushree Venkatesh

February 27, 2019

CoBot_architecture.jpg._CB453492855_.jpg

To ensure that Alexa Prize contestants can concentrate on dialogue systems — the core technology of socialbots — Amazon scientists and engineers built a set of machine learning modules that handle fundamental conversational tasks and a development environment that lets contestants easily mix and match existing modules with those of their own design.

Conversational AI

Updating neural networks to recognize new categories, with minimal retraining

Alessandro Moschitti

January 30, 2019

Many of today’s most popular AI systems are, at their core, classifiers. They classify inputs into different categories: this image is a picture of a dog, not a cat; this audio signal is an instance of the word “Boston”, not the word “Seattle”; this sentence is a request to play a video, not a song. But what happens if you need to add a new class to your classifier — if, say, someone releases a new type of automated household appliance that your smart-home system needs to be able to control?

Machine learning

Leveraging unannotated data to bootstrap Alexa functions more quickly

Anuj Goyal

January 22, 2019

Developing a new natural-language-understanding system usually requires training it on thousands of sample utterances, which can be costly and time-consuming to collect and annotate. That’s particularly burdensome for small developers, like many who have contributed to the library of more than 70,000 third-party skills now available for Alexa.

Conversational AI

New method for compressing neural networks better preserves accuracy

Anish Acharya, Rahul Goel

January 15, 2019

Neural networks have been responsible for most of the top-performing AI systems of the past decade, but they tend to be big, which means they tend to be slow. That’s a problem for systems like Alexa, which depend on neural networks to process spoken requests in real time.

Conversational AI

How Alexa may learn to retrieve stored "memories"

Rasool Fakoor

December 21, 2018

In May 2018, Amazon launched Alexa’s Remember This feature, which enables customers to store “memories” (“Alexa, remember that I took Ben’s watch to the repair store”) and recall them later by asking open-ended questions (“Alexa, where is Ben’s watch?”).

Search and information retrieval

How Alexa knows “peanut butter” is one shopping-list item, not two

Sanchit Agarwal

December 18, 2018

BIO_scheme_examples.png._CB459952676_.png

At a recent press event on Alexa's latest features, Alexa’s head scientist, Rohit Prasad, mentioned multistep requests in one shot, a capability that allows you to ask Alexa to do multiple things at once. For example, you might say, “Alexa, add bananas, peanut butter, and paper towels to my shopping list.” Alexa should intelligently figure out that “peanut butter” and “paper towels” name two items, not four, and that bananas are a separate item.

Conversational AI

With New Data Representation Scheme, Alexa Can Better Match Skills to Customer Requests

Young-Bum Kim

December 17, 2018

Representation_learning_architcture.png._CB459316582_.png

In recent years, data representation has emerged as an important research topic within machine learning.

Conversational AI

Natural-language understanding (NLU)

Work with us