For conversational AI and virtual assistants to communicate with humans in a realistic way, they must exhibit human characteristics such as expression of emotion and personality. Current attempts toward constructing human-like dialogue agents have presented significant difficulties. We propose Human Level Attributes (HLAs) based on tropes as the basis of a method for learning dialogue agents that can imitate the personalities of fictional characters. Tropes are characteristics of fictional personalities that are observed recurrently and determined by viewers' impressions. By combining detailed HLA data with dialogue data for specific characters, we present a dataset that models character profiles and gives dialogue agents the ability to learn characters' language styles through their HLAs. We then introduce a three-component system, ALOHA (which stands for Artificial Learning On Human Attributes), that combines character space mapping, character community detection, and language style retrieval to build a character (or personality) specific language model. Our preliminary experiments demonstrate that ALOHA, combined with our proposed dataset, can outperform baseline models at identifying correct dialogue responses of any chosen target character, and is stable regardless of the character's identity, genre of the show, and context of the dialogue.

Context modeling has a pivotal role in open domain conversation. Existing works either use heuristic methods or jointly learn context modeling and response generation with an encoder-decoder framework. This paper proposes an explicit context rewriting method, which rewrites the last utterance by considering context history. We leverage pseudo-parallel data and elaborate a context rewriting network, which is built upon the CopyNet with the reinforcement learning method. The rewritten utterance is beneficial to candidate retrieval, explainable context modeling, as well as enabling to employ a single-turn framework to the multi-turn scenario. The empirical results show that our model outperforms baselines in terms of the rewriting quality, the multi-turn response generation, and the end-to-end retrieval-based chatbots.

Critical infrastructure systems such as electric power networks, water networks, and transportation systems play a major role in the welfare of any community. In the aftermath of disasters, their recovery is of paramount importance; orderly and efficient recovery involves the assignment of limited resources (a combination of human repair workers and machines) to repair damaged infrastructure components. The decision maker must also deal with uncertainty in the outcome of the resource-allocation actions during recovery. The manual assignment of resources seldom is optimal despite the expertise of the decision maker because of the large number of choices and uncertainties in consequences of sequential decisions. This combinatorial assignment problem under uncertainty is known to be \mbox{NP-hard}. We propose a novel decision technique that addresses the massive number of decision choices for large-scale real-world problems; in addition, our method also features an experiential learning component that adaptively determines the utilization of the computational resources based on the performance of a small number of choices. Our framework is closed-loop, and naturally incorporates all the attractive features of such a decision-making system. In contrast to myopic approaches, which do not account for the future effects of the current choices, our methodology has an anticipatory learning component that effectively incorporates \emph{lookahead} into the solutions. To this end, we leverage the theory of regression analysis, Markov decision processes (MDPs), multi-armed bandits, and stochastic models of community damage from natural disasters to develop a method for near-optimal recovery of communities. Our method contributes to the general problem of MDPs with massive action spaces with application to recovery of communities affected by hazards.

A new bill will soon make it illegal to snoop on your neighbor with a drone. Called the Drone Integration and Zoning Act, the proposal deems airspace up to 200 feet over someone's home as their private property meaning punishments for trespassing could be enforced. The motion aims to distribute some of the Federal Aviation Administration's (FAA) authority over the nation's airspace to localities and private citizens by redefining'navigable airspace'. Sen. Mike Lee said from Utah, proposed the bill to congress on Wednesday stating, 'The FAA cannot feasibly or efficiently oversee millions of drones in every locality throughout the country.' 'The reason that the states have sovereign police powers to protect the property of their citizens is because issues of land use, privacy, trespass, and law enforcement make sense at the state and local level.' 'The best way to ensure public safety and allow this innovative industry to thrive is to empower the people closest to the ground to make local decisions in real time and that is exactly what the Drone Integration and Zoning Act does.'

Researchers at the University of Washington have devised a new app for smart speakers like Amazon's Echo to help parents monitor their baby's breathing. Called BreathJunior, the experimental app will be able to measure the rate of a baby's breathing and detect symptoms of sleep apnea. The team initially conducted a test of the device with five babies in the neonatal intensive care unit at a hospital in Washington. BreathJunior (pictured above) is an experimental app that monitors a baby's breathing using a smart speaker According to a report from MIT Tech Review, the team plans to eventually release the app as a commercial product via the company Sound Life Sciences. But first, they'll present the results of the trial at the upcoming MobiCom, a yearly conference on mobile computing in Los Cabos, Mexico.

The highly anticipated comprehensive study on robots, artificial intelligence and service automation in hospitality and tourism, edited by Varna University of Management's Vice Rector (Research) Prof. Stanislav Ivanov and Assoc. Prof. Craig Webster from the Department of Management at Ball State University, USA, is finally out today! "Robots, artificial intelligence and service automation in travel, tourism and hospitality" (RAISA in TTH) comprehensively covers the theoretical problems of RAISA adoption in tourism, principles of service automation, impacts of RAISA on business processes and competitiveness, and more, and at the same time focuses on the practical side of utilization of RAISA technologies in diverse tourism and hospitality entities. The book consists of 13 chapters, written by 31 researchers from 16 institutions and companies in 7 countries on 3 continents. Divided into two sections, the book first concentrates on the theoretical aspects surrounding the use of RAISA in travel, tourism and hospitality. Following on from this, the second section concentrates on current and future use of RAISA technologies in specific subsectors of the tourism economy: hotels, restaurants, travel agencies, museums, and events.

Last year in an article about speech analytics we told you 72 percent of companies thought speech analytics could allow for improved customer experience. In the piece, we mentioned Invoca as one of the players in the market. We've also covered the company more recently in a story about feelings and brand loyalty as well as another on CX metrics in the age of AI. The company's continued progress has caused investors to give them $56 million led by existing investor Upfront Ventures and new investor H.I.G. This latest funding round comes on the heels of 75% year-over-year bookings growth in the first half of 2019.

Working in call centers is not exactly a job that's spotlighted as enjoyable. For years, the industry was plagued by high turnover rates, agent burnout and other disjointed problems that were highlighted each time irate customers turned to online media to detail their experiences. In recent years, companies have put more focus on improving the work conditions in call centers so that agents feel more at ease and enjoy their jobs. When agents are happy, the project that happiness on to customers. After all, answering call after call and striving to achieve excellent service every time can be a daunting task.

Customer service is evolving, with innovation in areas like artificial intelligence, analytics and the Voice of the Customer we are on the precipice of wholesale change. The complex concert that is contact center operations is sounding quite sweet. Per recent reports from Frost & Sullivan (News - Alert) and DMG Consulting LLC, Verint has increased its market leadership in the Asia Pacific region. Echoing these sentiments, Frost & Sullivan named The Customer Engagement Company as the Contact Centre Optimization Solution of the Year. Krishna Baidya, Head – Customer Contact Research at Frost & Sullivan noted, "Verint's (News - Alert) strategy enables organizations to simplify, modernize, and automate their customer engagement operations and gain a sustainable competitive advantage, while balancing customer experience and cost in customer operations. The company has continuously expanded its analytics capabilities, strengthening all aspects of customer contact from agent performance optimization to customer and employee engagement."

Many advanced artificial intelligence projects say they are working toward building a conscious machine, based on the idea that brain functions merely encode and process multisensory information. The assumption goes, then, that once brain functions are properly understood, it should be possible to program them into a computer. Microsoft recently announced that it would spend US$1 billion on a project to do just that. So far, though, attempts to build supercomputer brains have not even come close. A multi-billion-dollar European project that began in 2013 is now largely understood to have failed.