Search results

We present and apply two methods for addressing the problem of selecting relevant training data out of a general pool for use in tasks such as machine translation. Building on existing work on class-based language difference models [1], we first introduce a cluster-based method that uses Brown clusters to condense the vocabulary of the corpora. Secondly, we implement the cynical data selection method [2

The Moore-Lewis method of “intelligent selection of language model training data” is very effective, cheap, efficient... and also has structural problems. (1) The method defines relevance by playing language models trained on the in-domain and the out-of-domain (or data pool) corpora against each other. This powerful idea – which we set out to preserve – treats the two corpora as the opposing ends of a

We study the problem of a retailer that maximizes profit through joint replenishment, pricing and removal decisions. This problem is motivated by the observation that retailers usually retain rights to remove inventory from their network either by returning it to the suppliers or through liquidation in the face of random demand and capacity constraints. We develop a tractable dynamic program by leveraging

Automatically understanding the plot of novels is important both for informing literary scholarship and applications such as summarization or recommendation. Various models have addressed this task, but their evaluation has remained largely intrinsic and qualitative. Here, we propose a principled and scalable framework leveraging expert-provided semantic tags (e.g., mystery, pirates) to evaluate plot representations

We present Pixie, a socialbot submitted to the 2017 Alexa Prize, developed with the objective of holding engaging casual conversations on open-ended topics. We discuss the modular, heterogeneous architecture of the Pixie system, and highlight the successes and shortcomings of our primarily template-based approach. We reflect on our findings about alternative paradigms used in the prototyping phase; in particular

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

In this work, we designed a conversational system by combining a finite state method, a retrieval model and a machine-initiative dialogue strategy. By using the machine-initiative strategy, most of the user queries are handled by the finite state machine which models predefined dialogues. If the user’s utterance is out of the range of modeled dialogues, the retrieval model processes the input. On comparative

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 this paper we introduce a novel, open domain socialbot for the Amazon Alexa Prize competition, aimed at carrying on friendly conversations with users on a variety of topics. We present our modular system, highlighting our different data sources and how we use the human mind as a model for data management. Additionally we build and employ natural language understanding and information retrieval tools

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

Open–domain dialogue systems should be able to cover a very large set of domains and at the same time keep the user engaged in the interaction. Current approaches to dialogue modeling are divided between domain–independent, non–modular approaches using sequence–to–sequence models and the domain–specific modular systems developed for task–based dialogue. Furthermore, user engagement in dialogue, addressed

This paper describes a new open domain dialogue system Alquist developed as part of the Alexa Prize competition for the Amazon Echo line of products. The Alquist dialogue system is designed to conduct a coherent and engaging conversation on popular topics. We are presenting a hybrid system combining several machine learning and rule based approaches. We discuss and describe the Alquist pipeline, data acquisition

We describe an information-oriented conversational AI system, EmersonBot, developed for the Alexa Prize 2017 competition. The main goal of the system was informing users about current events, and answering their questions, while maintaining a fluent conversation. The main innovations of Emersonbot include the development of a federated multi-source information retrieval system that is aware of the conversation

We describe our Alexa prize system (called ‘Alana’) which consists of an ensemble of bots, combining rule-based and machine learning systems, and using a contextual ranking mechanism to choose system responses. This paper reports on the version of the system developed and evaluated in the semi-finals of the competition (i.e. up to 15 August 2017), but not on subsequent enhancements. The ranker for this

This paper introduces the University of Washington’s Alexa Prize socialbot, Sound- ing Board, which is designed to engage users with a wide variety of content. The system models the user utterance using a multi-dimensional representation. A hierarchical dialogue manager is employed where a master manages the overall conversation and a collection of miniskills manage different conversation segments. The

Recent years have seen a surge in consumer usage of spoken dialog systems, due to the popularity of voice assistants. While these systems are capable of answering factual questions or executing basic tasks, they do not yet have the capability to hold multi-turn conversations. The Alexa Prize challenge provides us a great opportunity to explore various approaches and dialog strategies for building a multi-turn

RubyStar is a dialog system designed to create “human-like” conversation by combining different response generation strategies. RubyStar conducts a non- task-oriented conversation on general topics by using an ensemble of rule-based, retrieval-based and generative methods. Topic detection, engagement monitoring, and context tracking are used for managing interaction. Predictable elements of conversation

Sockeye is an open-source sequence-to-sequence framework for neural machine translation (NMT) built on PyTorch. It implements distributed training and optimized inference for state-of-the-art models, powering Amazon Translate and other MT applications. Recent developments and changes are tracked in our CHANGELOG. For a quickstart guide to training a standard NMT model on any size of data, see the WMT 2014

You can build smart home and other products that customers can control from millions of Alexa devices with just their voice. Expand your device’s capabilities with Alexa to create delightful experiences for lights, switches, thermostats, cameras, locks, and more. Plus, your Alexa-connected devices continue to become smarter with Alexa’s growing list of smart home capabilities and features that leverage