Search results

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 such as “Play the Prince song 1999” or “Play River by Joni Mitchell”. In each text, labels are attached to particular words — SongName for “1999” and “River”, for instance, and ArtistName for Prince and Joni Mitchell. By analyzing annotated data, the system learns to classify unannotated data on its own.

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 learned. British English, American English, and Indian English, for instance, are different enough that for each of them, we trained a new machine learning model from scratch.

New approach to reference resolution rewrites queries to clarify ambiguous references.

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

Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection of canonical online stochastic optimization problems with a range of practical applications: Bin Packing, Newsvendor, and Vehicle Routing. While there is a nascent literature that applies RL to these problems, there are no commonly

The Amazon Sustainability Data Initiative (ASDI) seeks to accelerate sustainability research and innovation by minimizing the cost and time required to acquire and analyze large sustainability datasets. ASDI supports innovators and researchers with the data, tools, and technical expertise they need to move sustainability to the next level. This repo contains docs, examples, and supporting material for ASDI

MLIO is a high performance data access library for machine learning tasks with support for multiple data formats. It makes it easy for scientists to train models on their data without worrying about the format or where it's stored. Algorithm developers can also use MLIO to build production-quality algorithms that support a rich variety of data formats and provide helpful parsing and validation messages

We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much

In this paper we study techniques to improve the performance of bilinear embedding methods for knowledge graph completion on large datasets, where at each epoch the model sees a very small percentage of the training data, and the number of generated negative examples for each positive example is limited to a small portion of the entire set of entities. We first present a heuristic method to infer the types

We introduce a method to generate vectorial representations of visual classification tasks that can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function, we process images through a “probe network” and compute an embedding based on estimates of the Fisher information matrix associated with the probe network parameters. This provides

We introduce Gluon Time Series (GluonTS)1, a library for deep-learning-based time series modeling. GluonTS simplifies the development of and experimentation with time series models for common tasks such as forecasting or anomaly detection. It provides all necessary components and tools that scientists need for quickly building new models, for efficiently running and analyzing experiments and for evaluating

The need for high-quality, large-scale, goal-oriented dialogue datasets continues to grow as virtual assistants become increasingly widespread. However, existing publicly available datasets useful for this area are limited either in their size, linguistic diversity, domain coverage, or annotation granularity. We introduce the MultiDoGO dataset to overcome these limitations. With a total of over 65,000 dialogues

Amazon SageMaker Debugger automates the debugging process of machine learning training jobs. From training jobs, Debugger allows you to run your own training script (Zero Script Change experience) using Debugger built-in features—Hook and Rule—to capture tensors, have flexibility to build customized Hooks and Rules for configuring tensors as you want, and make the tensors available for analysis by saving

This is a minimal implementation of the HTTP/1.0 and HTTP/1.1 protocols. This HTTP implementation is stateless thus it does not support chunking or compression. The micro-http implementation is used in production by Firecracker. As micro-http uses std::os::unix this crates only supports Unix-like targets.

Building socialbots that can have deep, engaging open-domain conversations with humans is one of the grand challenges of artificial intelligence (AI). To this end, bots need to be able to leverage world knowledge spanning several domains effectively when conversing with humans who have their own world knowledge. Existing knowledge-grounded conversation datasets are primarily stylized with explicit roles

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

Pre-trained models have demonstrated their effectiveness in many downstream natural language processing (NLP) tasks. The availability of multilingual pre-trained models enables zero-shot transfer of NLP tasks from high resource languages to low resource ones. However, recent research in improving pre-trained models focuses heavily on English. While it is possible to train the latest neural architectures

We present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task. The task challenged participants to both build systems to verify factoid claims using evidence retrieved from Wikipedia and to generate adversarial attacks against other participant’s systems. The shared task had three phases: building, breaking and fixing. There were 8 systems in the builder’s round, three of

Kernel methods are popular and effective techniques for learning on structured data, such as trees and graphs. One of their major drawbacks is the computational cost related to making a prediction on an example, which manifests in the classification phase for batch kernel methods, and especially in online learning algorithms. In this paper, we analyze how to speed up the prediction when the kernel function

The building block of Transformer can be seen as inducing message passing over a complete graph whose nodes correspond to input tokens. Such dense connections make the Transformer data-hungry. Star-Transformer exploits short-term dependencies more heavily by keeping the connections between adjacent tokens but relaying long dependencies via a central node, thereby reducing the number of connections from