Search results

Using machine learning to train information retrieval models — such as Internet search engines — is difficult because it requires so much manually annotated data. Of course, training most machine learning systems requires manually annotated data, but because information retrieval models must handle such a wide variety of queries, they require a lot of data. Consequently, most information retrieval systems rely primarily on mechanisms other than machine learning.

Earlier this month, Varun Sharma and Akshit Tyagi, two master’s students from the University of Massachusetts Amherst, began summer internships at Amazon, where, like many other scientists in training, they will be working on Alexa’s spoken-language-understanding systems.

Many of today’s most useful AI systems are multilabel classifiers: they map input data into multiple categories at once. An object recognizer, for instance, might classify a given image as containing sky, sea, and boats but not desert or clouds.

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.

In this paper we address the problem of detecting previously unseen novel audio events in the presence of real-life acoustic backgrounds. Specifically, during training, we learn subspaces corresponding to each acoustic background, and during testing the audio frame in question is decomposed into a component that lies on the mixture of subspaces and a super gaussian outlier component.Based on the energy

In this paper, we introduce an Augmented Lagrangian based method in a search relevance ranking algorithm to incorporate the multi-dimensional nature of relevance and business constraints, both of which are the requirements for building relevance ranking models in production. The off-the-shelf solutions cannot handle such complex objectives and therefore, modelers are left hand-tuning of parameters that

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

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

Modern deep learning applications urge to push the model inference taking place at the edge devices for multiple reasons such as achieving shorter latency, relieving the burden of the network connecting to the cloud, and protecting user privacy. The Convolutional Neural Network (CNN) is one of the most widely used model family in the applications. Given the high computational complexity of the CNN models

We examine the impact of "big data" on firm performance in the context of forecast accuracy using proprietary retail sales data obtained from Amazon. We measure the accuracy of forecasts in two relevant dimensions: the number of products (N), and the number of time periods for which a product is available for sale (T). Theory suggests diminishing returns to larger N and T, with relative forecast errors

Inspired by studies on the overwhelming presence of experience-sharing in human- human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conver- sational AI. The traditional approach of information-sharing topic handlers is balanced with a focus on opinion-oriented exchanges that Emora delivers, and new conversational

Tartan is a social bot that engages users in sharing daily personal experiences in multiple domains. Our work contributes to Conversational AI in two aspects: 1) We extract common-sense knowledge expressed in large-scale user utterances in conversations, and find that more than 20% of the shared information is related to personal life, such as social relationships and individual activities. 2) Based on

This report describes Athena, a dialogue system for spoken conversation on popular topics and current events. We develop a flexible topic-agnostic approach to dialogue management that dynamically configures dialogue based on general principles of entity and topic coherence. Athena’s dialogue manager uses a contract-based method where discourse constraints are dispatched to clusters of response generators

We propose Bernard: a framework for an engaging open-domain socialbot. While the task of open-domain dialog generation remains a difficult one, we explore various strategies to generate coherent dialog given an arbitrary dialog history. We incorporate a stateful autonomous dialog manager using non-deterministic finite automata to control multi-turn conversations. We show that powerful pretrained language

With the launch of Alexa in 2014, Amazon sparked a renaissance in conversational AI. Combining far-field speech recognition with state-of-the-art natural language understanding, Alexa captured the imagination of millions of users worldwide. All of them had discovered that speech is, indeed, the most natural of user interfaces! In the summer of 2015, the Alexa Skills Kit (ASK) was launched with the goal

Building conversational systems that enable natural language interactions with machines has been an attractive research area since the early days of computing, as exemplified by earlier text-based systems such as ELIZA [Weizenbaum, 1966]. The research and development work in this area has been increasing since then, with many publications on both task-oriented [Hosseini-Asl et al, 2020; Papangelis et al

We present Chirpy Cardinal, an open-domain dialogue agent, as a research plat- form for the 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people is challenging – such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection. Our socialbot engages users on their terms – prioritizing their interests, feelings