Search results

In this document we outline the data collection methods, system, and experiments we ran during the course of this project. We aim to shed light on what drove the development of our bot and the techniques we used to power our bot in the course of the conversation.

In recent years, chat-bots that assist people’s daily life gained tremendous popular- ity, such as Siri, Cortana, Alexia and Google assistant. Typically, conversations with chat-bots are task orientated and brief. In this work, we explore creating social bot that can complete task and entertain user. We proposed a two-layered dialogue framework which allows for flexible reuse and reorganization of individual

Edina is a conversational agent whose responses utilize data harvested from Amazon Mechanical Turk (AMT) through an innovative new technique we call self-dialogues. These are conversations in which a single AMT Worker plays both participants in a dialogue. Such dialogues are surprisingly natural, efficient to collect and reflective of relevant and/or trending topics. These self-dialogues provide training

We present a novel, large-scale ensemble-based system for the Amazon Alexa Prize competition. Our system leverages state-of-the-art methods from deep learning and reinforcement learning. We carry out A/B testing experiments with real-world users and demonstrate that our approach yields substantial improvements over several baseline systems. During the competition semi-finals, our best performing system

We propose a new smart local search for the p-center problem, based on the critical vertex concept, and embed it in a GRASP framework. Experimental results attest the robustness of the proposed search procedure and confirm that for benchmark instances it converges to optimal or near/optimal solutions faster than the best known state-of-the-art local search.

Estimating the relevance of documents based on the user feedback is an essential component of search, retrieval and ranking problems. User click modeling in search has focused primarily on factoring out the position bias. It is easy to see that the query type (generic queries vs specific queries) and user intent (purchase vs exploration) also introduce a bias in the click signal. In other words, the results

Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural language understanding (NLU) errors. In this paper, we focus on learning robust dialog policies to recover from these errors. To this end, we develop a user simulator

A challenge for speech recognition for voice-controlled household devices, like the Amazon Echo or Google Home, is robustness against interfering background speech. Formulated as a far-field speech recognition problem, another person or media device in proximity can produce background speech that can interfere with the device-directed speech. We expand on our previous work on device-directed speech detection

Conversational agents are exploding in popularity. However, much work remains in the area of social conversation as well as free-form conversation over a broad range of domains and topics. To advance the state of the art in conversational AI, Amazon launched the Alexa Prize, a 2.5-million-dollar university competition where sixteen selected university teams were challenged to build conversational agents

We present a platform built on large-scale, data-centric machine learning (ML) approaches, whose particular focus is demand forecasting in retail. At its core, this platform enables the training and application of probabilistic demand forecasting models, and provides convenient abstractions and support functionality for forecasting problems. The platform comprises of a complex end-to-end machine learning

Finding sustainable products and evaluating their claims is a significant barrier facing sustainability-minded customers. Tools that reduce both these burdens are likely to boost the sale of sustainable products. However, it is difficult to determine the sustainability characteristics of these products — there are a variety of certifications and definitions of sustainability, and quality labeling requires

Topical PageRank (TPR) uses latent topic distribution inferred by Latent Dirichlet Allocation (LDA) to perform ranking of noun phrases extracted from documents. The ranking procedure consists of running PageRank K times, where K is the number of topics used in the LDA model. In this paper, we propose a modification of TPR, called Salience Rank. Salience Rank only needs to run PageRank once and extracts

E-commerce websites such as Amazon, Alibaba, Flipkart, and Walmart sell billions of products. Machine learning (ML) algorithms involving products are often used to improve the customer experience and increase revenue, e.g., product similarity, recommendation, and price estimation. The products are required to be represented as features before training an ML algorithm. In this paper, we propose an approach

We study the generalization error of randomized learning algorithms—focusing on stochastic gradient descent (SGD)—using a novel combination of PAC-Bayes and algorithmic stability. Importantly, our generalization bounds hold for all posterior distributions on an algorithm’s random hyperparameters, including distributions that depend on the training data. This inspires an adaptive sampling algorithm for SGD

Conversational agents are exploding in popularity. However, much work remains in the area of non goal-oriented conversations, despite significant growth in research interest over recent years. To advance the state of the art in conversational AI, Amazon launched the Alexa Prize, a 2.5-million dollar university competition where sixteen selected university teams built conversational agents to deliver the

In this work, we develop a technique for training features directly from the single-channel speech waveform in order to improve wake word (WW) detection performance. Conventional speech recognition systems typically extract a compact feature representation based on prior knowledge such as log-mel filter bank energy (LFBE). Such a feature is then used for training a deep neural network (DNN) acoustic model

We present a zero-shot learning approach for text classification, predicting which natural language understanding domain can handle a given utterance. Our approach can predict domains at runtime that did not exist at training time. We achieve this extensibility by learning to project utterances and domains into the same embedding space while generating each domain-specific embedding from a set of attributes

In this paper we investigate a time delay neural network (TDNN) for a keyword spotting task that requires low CPU, memory and latency. The TDNN is trained with transfer learning and multi-task learning. Temporal subsampling enabled by the time delay architecture reduces computational complexity. We propose to apply singular value decomposition (SVD) to further reduce TDNN complexity. This allows us to first

Amazon Aurora is a relational database service for OLTP workloads offered as part of Amazon Web Services (AWS). In this paper, we describe the architecture of Aurora and the design considerations leading to that architecture. We believe the central constraint in high throughput data processing has moved from compute and storage to the network. Aurora brings a novel architecture to the relational database

Automatic speech recognition is now playing an important role in volume control and adjustment of modern smart speakers. According to the recognition results by using the advanced deep neural network technology, this paper proposes an efficient processing system for automatic volume control (AVC) and limiter. The theoretical analyses, subjective and objective testing results show that the proposed processing