Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches to provide insights toward the model's behavior and predictions, which are helpful for determining the reliability of the model's prediction. However, such methods do not fix and improve the model's reliability. In this paper, we teach our models to make the right prediction for the right reason by providing explanation training signal and ensuring alignment of the models explanation with the ground truth explanation. Our experimental results on multiple tasks and datasets demonstrate the effectiveness of the proposed method, which produces more reliable predictions while delivering better results compared to traditionally trained models.

In many social situations, a discrepancy arises between an individual's private and expressed opinions on a given topic. Motivated by Solomon Asch's seminal experiments on social conformity and other related socio-psychological works, we propose a novel opinion dynamics model to study how such a discrepancy can arise in general social networks of interpersonal influence. Each individual in the network has both a private and an expressed opinion: an individual's private opinion evolves under social influence from the expressed opinions of the individual's neighbours, while the individual determines his or her expressed opinion under a pressure to conform to the average expressed opinion of his or her neighbours, termed the local public opinion. General conditions on the network that guarantee exponentially fast convergence of the opinions to a limit are obtained. Further analysis of the limit yields several semi-quantitative conclusions, which have insightful social interpretations, including the establishing of conditions that ensure every individual in the network has such a discrepancy. Last, we show the generality and validity of the model by using it to explain and predict the results of Solomon Asch's seminal experiments.

Generalization to unknown/uncertain environments of reinforcement learning algorithms is crucial for real-world applications. In this work, we explicitly consider uncertainty associated with the test environment through an uncertainty set. We formulate the Distributionally Robust Reinforcement Learning (DR-RL) objective that consists in maximizing performance against a worst-case policy in uncertainty set centered at the reference policy. Based on this objective, we derive computationally efficient policy improvement algorithm that benefits from Distributionally Robust Optimization (DRO) guarantees. Further, we propose an iterative procedure that increases stability of learning, called Distributionally Robust Policy Iteration. Combined with maximum entropy framework, we derive a distributionally robust variant of Soft Q-learning that enjoys efficient practical implementation and produces policies with robust behaviour at test time. Our formulation provides a unified view on a number of safe RL algorithms and recent empirical successes.

The dramatic success in machine learning has led to an explosion of artificial intelligence (AI) applications and increasing expectations for autonomous systems that exhibit human-level intelligence. These expectations have, however, met with fundamental obstacles that cut across many application areas. One such obstacle is adaptability, or robustness. Machine learning researchers have noted current systems lack the ability to recognize or react to new circumstances they have not been specifically programmed or trained for. Intensive theoretical and experimental efforts toward "transfer learning," "domain adaptation," and "lifelong learning"4 are reflective of this obstacle. Another obstacle is "explainability," or that "machine learning models remain mostly black boxes"26 unable to explain the reasons behind their predictions or recommendations, thus eroding users' trust and impeding diagnosis and repair; see Hutson8 and Marcus.11 A third obstacle concerns the lack of understanding of cause-effect connections.

Artificial intelligence is taking over more and more jobs. The NYT reports that more and more journalism is actually being written by robots including nearly 1/3 of Bloomberg articles. "robot reporters have been prolific producers of articles on minor league baseball for The Associated Press, high school football for The Washington Post and earthquakes for The Los Angeles Times… Last week, The Guardian's Australia edition published its first machine-assisted article, an account of annual political donations to the country's political parties. And Forbes recently announced that it was testing a tool called Bertie to provide reporters with rough drafts and story templates… The Wall Street Journal and Dow Jones are experimenting with the technology to help with various tasks, including the transcription of interviews… Patch [is] a nationwide news organization devoted to local news, [with] 110 staff reporters and numerous freelancers who cover about 800 communities… In a given week, more than 3,000 posts on Patch -- 5 to 10 percent of its output -- are machine-generated… "One thing I've noticed," Mr. St. John said, "is that our A.I.-written articles have zero typos."

As email continues to be not only an important means of communication but also an official record of information and a tool for managing tasks, schedules, and collaborations, making sense of everything moving in and out of our inboxes will only get more difficult. The good news is there's a method to the madness of staying on top of your email, and Microsoft researchers are drawing on this behavior to create tools to support users. Two teams working in the space will be presenting papers at this year's ACM International Conference on Web Search and Data Mining February 11–15 in Melbourne, Australia. "Identifying the emails you need to pay attention to is a challenging task," says Partner Researcher and Research Manager Ryen White of Microsoft Research, who manages a team of about a dozen scientists and engineers and typically receives 100 to 200 emails a day. "Right now, we end up doing a lot of that on our own."

Most business leaders and entrepreneurs today realise that artificial intelligence (AI) is essential for the growth and competitiveness of their organizations. In fact, the AI technology will allow the rate of innovation and employee productivity improvements in Asia Pacific to nearly double (1.9 times, to be precise) by 2021, according to business leaders in the Asia-Pacific (APAC) region. These were some of the findings of a study from Microsoft and IDC Asia/Pacific, "Future Ready Business: Assessing Asia's Growth Potential Through AI", which surveyed over 1,600 business leaders and over 1,580 workers across 15 markets, including Australia, China, Hong Kong, Indonesia, India, Japan, Korea, Malaysia, New Zealand, Philippines, Singapore, Sri Lanka, Taiwan, Thailand and Vietnam. Among the industries polled included agriculture, automotive, education, financial services, government, healthcare, manufacturing, retail, services and telco/media. Eight in 10 business leaders from companies with more than 250 staff agreed that AI is instrumental for their organization's competitiveness, the study said.

Most business leaders and entrepreneurs today realise that artificial intelligence (AI) is essential for the growth and competitiveness of their organizations. In fact, the AI technology will allow the rate of innovation and employee productivity improvements in Asia Pacific to nearly double (1.9 times, to be precise) by 2021, according to business leaders in the Asia-Pacific (APAC) region. These were some of the findings of a study from Microsoft and IDC Asia/Pacific, "Future Ready Business: Assessing Asia's Growth Potential Through AI", which surveyed over 1,600 business leaders and over 1,580 workers across 15 markets, including Australia, China, Hong Kong, Indonesia, India, Japan, Korea, Malaysia, New Zealand, Philippines, Singapore, Sri Lanka, Taiwan, Thailand and Vietnam. Among the industries polled included agriculture, automotive, education, financial services, government, healthcare, manufacturing, retail, services and telco/media. Eight in 10 business leaders from companies with more than 250 staff agreed that AI is instrumental for their organization's competitiveness, the study said.

After years of quiet percolation, the art world is suddenly waking up to the creative and market potential of AI-generated art. Earlier this year, the Grand Palais museum in Paris staged a show examining the medium, and this month, Christie's announced it will be auctioning off a work made by an artificial intelligence in October. Now, one of the largest contemporary commercial galleries in India, Nature Morte, has become the first mainstream gallery to take the nascent art form seriously. "Gradient Descent," on view through September 15 at the New Delhi gallery, is a group show including works created entirely by computers in collaboration with seven international artists: Harshit Agrawal, Memo Akten, Jake Elwes, Mario Klingemann, Anna Ridler, Nao Tokui, and Tom White. Gallery director Aparajita Jain tells artnet News that it couldn't afford to ignore the field of AI-made art because of how she believes it is going to impact the art world. And while she was initially shocked to find out how far AI has already come in the creative field, Jain wants to dispel the idea that it will replace artists in the same way it is replacing human workers in other fields.

As artificial intelligence (AI) and chatbots start to infiltrate the digital workplace it's been interesting to watch the emergence of the "enterprise digital assistant" concept. While "digital assistant" may conjure up cute images of robot helpers, they are effectively apps that act as an interface with other systems to aid in task completion and search. In some cases, they include a chat interface and possibly even a little machine learning thrown in for good measure. The concept is persuasive -- who wouldn't want a friendly, convenient digital assistant that works quietly in the background to help you get things done? Offering an enterprise digital assistant can tick the "we are doing something about AI" box for potential new hires, who arguably might find this attractive.