Search results

In June 2018, Amazon announced the 11 focus areas of the 2018 Amazon Research Awards.

Amazon Alexa currently has more than 40,000 third-party skills, which customers use to get information, perform tasks, play games, and more. To make it easier for customers to find and engage with skills, we are moving toward skill invocation that doesn’t require mentioning a skill by name (as highlighted in a recent post).

Alexa is a cloud-based service with natural-language-understanding capabilities that powers devices like Amazon Echo, Echo Show, Echo Plus, Echo Spot, Echo Dot, and more. Alexa-like voice services traditionally have supported small numbers of well-separated domains, such as calendar or weather. In an effort to extend the capabilities of Alexa, Amazon in 2015 released the Alexa Skills Kit, so third-party developers could add to Alexa’s voice-driven capabilities. We refer to new third-party capabilities as skills, and Alexa currently has more than 40,000.

Developing a new Alexa skill typically means training a machine-learning system with annotated data, and the skill’s ability to “understand” natural-language requests is limited by the expressivity of the semantic representation used to do the annotation. So far, the techniques used to represent natural language have been fairly simple, so Alexa has been able to handle only relatively simple requests.

Tree-structured LSTMs have shown advantages in learning semantic representations by exploiting syntactic information. Most existing methods model tree structures by bottomup combinations of constituent nodes using the same shared compositional function and often making use of input word information only. The inability to capture the richness of compositionality makes these models lack expressive power.

Recent speech synthesis systems based on sampling from autoregressive neural networks models can generate speech almost undistinguishable from human recordings. However, these models require large amounts of data. This paper shows that the lack of data from one speaker can be compensated with data from other speakers. The naturalness of Tacotron2-like models trained on a blend of 5k utterances from 7 speakers

The state of the art in probabilistic demand forecasting [40] minimizes Quantile Loss to predict the future demand quantiles for different horizons. However, since quantiles aren’t additive, in order to predict the total demand for any wider future interval all required intervals are usually appended to the target vector during model training. The separate optimization of these overlapping intervals can

The current most popular method for automatic Natural Language Generation (NLG) evaluation is comparing generated text with human-written reference sentences using a metrics system, which has drawbacks around reliability and scalability. We draw inspiration from second language (L2) assessment and extract a set of linguistic features to predict human judgments of sentence naturalness. Our experiment using

We propose an alternative training framework for Bayesian neural networks (BNNs), which is motivated by viewing the Bayesian model for supervised learning as an autoencoder for data transmission. Then, a natural objective can be invoked from the rate-distortion theory. Specifically, we end up minimizing the mutual information between the weights and the dataset with a constraint that the negative log-likelihood

Building open domain conversational systems that allow users to have engaging conversations on topics of their choice is a challenging task. Alexa Prize was launched in 2016 to tackle the problem of achieving natural, sustained, coherent and engaging open-domain dialogs. In the second iteration of the competition in 2018, university teams advanced the state of the art by using context in dialog models,

Deep neural networks are often brittle to superficial perturbations of their inputs; models that perform well offline on held-out data can still break under small amounts of naturally-occurring or adversarial shifts. We consider invariant representation learning (IRL), first proposed in the domain of speech recognition, as a simple, effective, and general extension to data augmentation. Rather than only

Goal-oriented dialogue systems typically rely on components specifically developed for a single task or domain. This limits such systems in two different ways: If there is an update in the task domain, the dialogue system usually needs to be updated or completely re-trained. It is also harder to extend such dialogue systems to different and multiple domains. The dialogue state tracker in conventional dialogue

Managing risk is important to any E-commerce merchant. Various machine learning (ML) models combined with a rule set as the decision layer is a common practice to manage the risks. Unlike the ML models that can be automatically refreshed periodically based on new risk patterns, rules are generally static and rely on manual updates. To tackle that, this paper presents a data-driven and automated rule optimization

This article presents a whisper speech detector in the far-field domain. The proposed system consists of a long short-term memory (LSTM) neural network trained on log-filterbank energy (LFBE) acoustic features. This model is trained and evaluated on recordings of human interactions with voice-controlled, far-field devices in whisper and normal phonation modes. We compare multiple inference approaches for

Multi-fidelity methods are prominently used when cheaply-obtained, but possibly biased and noisy, observations must be effectively combined with limited or expensive true data in order to construct reliable models. This arises in both fundamental machine learning procedures such as Bayesian optimization, as well as more practical science and engineering applications. In this paper we develop a novel multi-fidelity

Building conversational systems that enable natural language interactions with machines has been attractive to mankind since the early days of computing, as exemplified by earlier text-based systems such as ELIZA [Weizenbaum, 1966]. Previous work on conversational systems generally falls into two categories, task-oriented and socialbots. Task-oriented systems aim to help users accomplish a specific task

In September 2016, Amazon introduced a new problem in conversational Al, the Alexa Prize, which challenged student teams to build a socialbot that could converse with Alexa on a wide range of topics. The socialbot differs from task-oriented dialog systems that address explicit user goals associated with a constrained domain, and also differs from chatbot systems that only handle social chitchat. The socialbot

This paper presents the second version of the dialogue system named Alquist competing in Amazon Alexa Prize 2018. We introduce a system leveraging ontology based topic structure called topic nodes. Each of the nodes consists of several sub-dialogues, and each sub-dialogue has its own LSTM-based model for dialogue management. The sub-dialogues can be triggered according to the topic hierarchy or a user intent

We describe our 2018 Alexa prize system (called ‘Alana’) which consists of an ensemble of bots, combining rule-based and machine learning systems. This paper reports on the version of the system developed and evaluated in the semifinals of the 2018 competition (i.e. up to 15 August 2018), but not on subsequent enhancements. The main advances over our 2017 Alana system are: (1) a deeper Natural Language

We describe IrisBot, a conversational agent that aims to help a customer be informed about the world around them, while being entertained and engaged. Our bot attempts to incorporate real-time search, informed advice, and latest news recommendation into a coherent conversation. IrisBot can already track information on the latest topics and opinions from News, Sports, and Entertainment and some specialized