Learning to control the structure of sentences is a challenging problem in text generation. Existing work either relies on simple deterministic approaches or RL-based hard structures. We explore the use of structured variational autoencoders to infer latent templates for sentence generation using a soft, continuous relaxation in order to utilize reparameterization for training. Specifically, we propose a Gumbel-CRF, a continuous relaxation of the CRF sampling algorithm using a relaxed Forward-Filtering Backward-Sampling (FFBS) approach. As a reparameterized gradient estimator, the Gumbel-CRF gives more stable gradients than score-function based estimators. As a structured inference network, we show that it learns interpretable templates during training, which allows us to control the decoder during testing. We demonstrate the effectiveness of our methods with experiments on data-to-text generation and unsupervised paraphrase generation.
Excelling customer service has never been more important for businesses. Today, businesses are adopting AI-powered digital solutions to improve customer support operations and outdo their competition. Let's have a look at how artificial intelligence can help your business ace customer support. With advanced systems powered by automated solutions, customers can now reserve a table at a restaurant, order a pizza, book a movie ticket, hotel room, and even make a clinic appointment. The customer service industry is gaining much momentum especially due to automation powered by artificial intelligence.
Natural language programming is a promising approach to enable end users to instruct new tasks for intelligent agents. However, our formative study found that end users would often use unclear, ambiguous or vague concepts when naturally instructing tasks in natural language, especially when specifying conditionals. Existing systems have limited support for letting the user teach agents new concepts or explaining unclear concepts. In this paper, we describe a new multi-modal domain-independent approach that combines natural language programming and programming-by-demonstration to allow users to first naturally describe tasks and associated conditions at a high level, and then collaborate with the agent to recursively resolve any ambiguities or vagueness through conversations and demonstrations. Users can also define new procedures and concepts by demonstrating and referring to contents within GUIs of existing mobile apps. We demonstrate this approach in PUMICE, an end-user programmable agent that implements this approach. A lab study with 10 users showed its usability.
The travel industry is one of the biggest proponents and early adopters of AI technology and applications. AI and machine learning are a natural fit for travel, a somewhat volatile industry that ebbs and flows based on a large number of wildcard variables. Customer service has been the primary way AI is being steadily integrated into the travel experience, although there are a host of other potential applications for the technology. Hotels are a prime location for AI adoption and the Connie robot being deployed by Hilton Worldwide Hotels is one of the most well known examples. Connie is an AI-based concierge that uses AI and speech recognition to provide a variety of tourist-related information to guests who speak to it.
In the 21st century, industries that remain adamant to integrating new technological revolutions are most likely to regress in their course of development. Businesses across the globe have realized how important it is to include contemporary digital technology to drive constant growth and revenue. The last decade has seen incredible innovations and breakthroughs in the landscape of digital solutions. One of such compelling technologies is called Artificial Intelligence (AI). Often misconceived as a replacement for human power, the concept of AI as a technological aid is much larger, wider and pervasive.
Automation of services has picked up its fastest pace by now, giving users the much needed facility to fulfill their regular tasks. With advanced systems powered by automated solutions, users can now book a restaurant reservation, order a pizza, book a movie ticket, hotel room and even make a clinic appointment. Customer service industry is gaining much momentum especially due to disruption of Artificial Intelligence – a technological breakthrough that has taken almost every business industry by storm. By transforming customer service interactions, AI-powered digital solutions are prepared to improve every aspect of your business including online customer experience, loyalty, brand reputation, preventive assistance and even generation of revenue streams. Digital market moguls project that by 2020 more than 85% of all customer support communications will be conducted without engaging any customer service representatives.
In this paper we survey the methods and concepts developed for the evaluation of dialogue systems. Evaluation is a crucial part during the development process. Often, dialogue systems are evaluated by means of human evaluations and questionnaires. However, this tends to be very cost and time intensive. Thus, much work has been put into finding methods, which allow to reduce the involvement of human labour. In this survey, we present the main concepts and methods. For this, we differentiate between the various classes of dialogue systems (task-oriented dialogue systems, conversational dialogue systems, and question-answering dialogue systems). We cover each class by introducing the main technologies developed for the dialogue systems and then by presenting the evaluation methods regarding this class.
Artificial Intelligence (AI) may look like something out of the pages of a sci-fi book, yet you'd be surprised how often you use it daily. As the technology continues to improve, AI will become even more common with more widespread utilization among diverse industries. To start with, let's begin with the basic definition of Artificial Intelligence (AI) and what it includes. Seeking Alpha gives a very apt description of the same in their article- At a basic level, artificial intelligence is the concept of machines accomplishing tasks which have historically required human intelligence. Applied AI: Machines designed to complete very specifics tasks like navigating a vehicle, trading stocks, or playing chess – as IBM's Deep Blue demonstrated in 1996 when it defeated chess grand master Gerry Kasparov. General AI: Machines designed to complete any task which would normally require human intervention. The broad nature of General AI requires machines to "learn" as they encounter new tasks or ...
Instead it is about a thoroughly progressive, completely 360 degree view of the traveller and everything that goes into creating special, unique, memorable experiences." Did you get your tickets directly from the ticket office? In today's fast-paced world, finding time to travel to a ticket office and get your tickets is a luxury few can afford. Besides, why bother if you can get your tickets in just a couple of clicks via your laptop or even your smartphone? Indeed, digital travel sales grew rapidly over the last several years, totaling $564.87 billion in 2016. And the number is expected to reach $817.54 billion by 2020. Such explosive growth is fueled by recent technology advances, not the least of which is data science. We at AltexSoft are no strangers to successfully applying data science and machine learning technologies to the field of custom travel software development.
The problem with all new hotel technology, unfortunately, is that innovation gets turned into buzzwords quickly, usually in order to sell more products and services. Even worse, all these buzzwords are thrown into the same marketing pot, creating a vast confusion that only "experts" can understand. With this article and accompanying infographic, we will demystify this subject of artificial intelligence (AI) and explain, in plain terms, what it is and what it means for hotels. This guide was created with the intention of clarifying the most important terms and concepts related to artificial intelligence and shedding some light on what AI really means for hotels, without technicalities and by providing easy-to-understand industry examples. Note: This article is also available as a PDF to download here. "What is a lobby boy?