Today's virtual personal assistants are conversational, voice-enabled artificial intelligence (AI) backed innovations that can communicate, learn, and intelligently predict an individual's needs to offer truly personalized experiences. Earlier this year, HARMAN and MSC Cruises introduced a groundbreaking virtual personal assistant as part of the cruise line's digital innovation program. By offering guests quick and easy answers about cruise events and entertainment from the comfort of their own cabin, the digital assistant can help simplify and enhance passengers' cruise experience. However, this new, progressive service is a mere drop in the ocean when it comes to the infinite number of ways that AI stands to revolutionize the hospitality industry. The hospitality and travel industry is no stranger to technological transformations, and it is on the cusp of a new revolution with the introduction of digital assistants and voice-enabled technology.

The proliferation of chatbot madness did not start today. Introduced by Alan Turing, chatbox begun in the 1950s. The artificial intelligence industry is growing exponential with 2014 statistics showing that the artificial intelligence has hit $126 billion. One of the reasons for the rapid growth of chatbox popularity is that many companies around the world have started adding virtual assistant bots for the purposes of customer service. Initially, chatbots were created to identify keywords, patterns, and keywords and the earned the reputation of being one of the most sophisticated programs.

Generative Text-to-Speech Synthesis, Heiga Zen, Research Scientist Abstract: Recent progress in deep generative models and its application to text-to-speech (TTS) synthesis has made a breakthrough in the naturalness of artificially generated speech.

My goal in this post is simply to share how we at YouVersion are leveraging machine learning tools to generate product recommendations. This article does not aim to teach fundamentals of machine learning or data science (as if one post even could do that), but it does aim to help others considering building a recommendation engine by seeing how we approached the problem. The tools and libraries mentioned as a part of this should be considered, but they should not be seen as promoted or the only way to build this kind of a system. They are simply what we utilized to accomplish our goal. At YouVersion, our goal is to lead people to engage with Bible scripture.

YouTube's T.J. Fowler explains how the Google Assistant can make better music suggestions on YouTube's revamped Music service A link has been sent to your friend's email address. A link has been posted to your Facebook feed. YouTube's T.J. Fowler explains how the Google Assistant can make better music suggestions on YouTube's revamped Music service USA TODAY

Recommender system has been demonstrated as a successful solution to assist decision makings. Context-awareness becomes necessity in recommendations, especially in mobile computing, since a user's decision may vary from contexts to contexts. Context-aware recommender systems, therefore, emerged to adapt the personalizations to different contextual situations. Context filtering is one of the popular ways to develop the context-aware recommendation models. Contextual pre-filtering techniques have been well developed, but the post-filtering methods are still under investigated. In this paper, we propose a simple but effective post-filtering recommendation approach. We demonstrate the effectiveness of this algorithm in comparison with other context-aware recommendation approaches based on the real-world rating data from mobile applications. Our experimental results reveal that the proposed algorithm is the best post-filtering approach, and it is even able to outperform the popular pre-filtering and contextual modeling recommendation models.

One of the most significant contributions to decision technology is multi-attribute utility (MAU) theory. MAU has gained increased traction in determining the value of information in tactical networking, has been a inspiration for some content-based recommender systems, and artifacts of MAU can be found on nearly every e-commerce website. While recommender systems attempt to create a model of the user (often on latent variables) from rating data, MAU attempts to solicit content-relevant attribute weightings explicitly. Both of these methods have trade-offs which might be mitigated if they could be combined. This research presents a method that we call MAUSVR for fusing recommender and MAU decision technology by automatically learning MAU models (from a user's ratings. A comparison with collaborative filtering techniques on the MovieLens dataset suggests that MAUSVR achieves better ranking quality under sparse conditions while also gaining in transparency and locality. Additionally, MAUSVR was able to be built instantaneously (< 100ms) for more than 75% of the evaluated users with an off-the shelf Java implementation of SMOreg. These findings indicate promise for the use of MAUSVR in real-time decision support systems operating in sparse data conditions.

The success of a recommender system lies in capturing preferences of users and recommending products that best cater to their needs. We restrict our focus to knowledge based recommender systems where we have the flexibility to model users preferences on individual features of the product. In this work, along with learning users preferences, we bring in the idea of looking at the problem of recommending from the manufacturer's point of view. We model prospective buyers of each product in the domain and use this information in predicting products that would potentially be of interest to a given user.

Recommender systems are being used to suggest products to customers, provide personalized product information, and even to provide product reviews. ese systems recommend items among a huge number of possibilities according to users' interests. Recommender systems have al- so been proposed to support the information selection and decision-making processes on e-com- merce web sites. is is the fourth recommender systems special track running in parallel with FLAIRS. The goal of this new special track has been to provide a forum for researchers and practitioners to share their e orts in addressing current issues, challenges, novel approaches, and applica- tions within the broad scope of recommender systems. We continue to aim to cover a wide variety of research areas where recommender systems may be researched and applied.

This paper presents a reading recommendation system based on morpho-phonological, lexical, and syntactic features reflecting both textual complexity and the learner’s linguistic proficiency. The goal of this system is to optimize the reading process of ESL learners by proposing the fittest text to their needs given their incrementally built profile (weighted history of read texts). Fifteen features out of an initial pool of 90 candidates were selected. A corpus of 5052 texts of different levels was collected and used to build the system. To make the system more adaptive, a Progress Rate (PRate) measure was also proposed and integrated into the search process. Finally, the evaluation of the system showed positive results.