Community Question Answering (cQA) provides new interesting research directions to the traditional Question Answering (QA) field, e.g., the exploitation of the interaction between users and the structure of related posts. In this context, we organized SemEval-2015 Task 3 on "Answer Selection in cQA", which included two subtasks: (a) classifying answers as "good", "bad", or "potentially relevant" with respect to the question, and (b) answering a YES/NO question with "yes", "no", or "unsure", based on the list of all answers. We set subtask A for Arabic and English on two relatively different cQA domains, i.e., the Qatar Living website for English, and a Quran-related website for Arabic. We used crowdsourcing on Amazon Mechanical Turk to label a large English training dataset, which we released to the research community. Thirteen teams participated in the challenge with a total of 61 submissions: 24 primary and 37 contrastive. The best systems achieved an official score (macro-averaged F1) of 57.19 and 63.7 for the English subtasks A and B, and 78.55 for the Arabic subtask A.

Reinforcement learning in a multi agent system is difficult because these systems are inherently non-stationary in nature. In such a case, identifying the type of the opposite agent is crucial and can help us address this non-stationary environment. We have investigated if we can employ some probing policies which help us better identify the type of the other agent in the environment. We've made a simplifying assumption that the other agent has a stationary policy that our probing policy is trying to approximate. Our work extends Environmental Probing Interaction Policy framework to handle multi agent environments.

In 2018 we saw a number of landmark research breakthroughs in the field of natural language processing (NLP). The introduction of transfer learning and pretrained language models in NLP pushed forward the limits of language understanding and generation. These also dominated NLP progress this year. Teams from top research institutions and tech companies explored ways to make state-of-the-art language models even more sophisticated. Many improvements were driven by massive boosts in computing capacities, but many research groups also discovered ingenious ways to lighten models while maintaining high performance. In this article, we summarize 11 research papers covering key language models presented during the year as well as recent research breakthroughs in machine translation, sentiment analysis, dialogue systems, and abstractive summarization.

Companies are already making sophisticated marketing decisions with data and analytics. Will deep learning enable a leap forward -- or just marginal gains? Deep learning is delivering impressive results in AI applications. Apple's Siri, for example, translates the human voice into computer commands that allow iPhone owners to get answers to questions, send messages, and navigate their way to and from obscure locations. Automated driving enables people today to go hands-free on expressways, and it will eventually do the same on city streets.

If you have massive amounts of data you want to use for machine learning or deep learning, you'll need people to enrich it so you can train, validate, and tune your model. Our transparent process provides an agile and scalable approach elevating accuracy, consistency, and speed. Our unique combination of people who care, process excellence, and platform capabilities is the hallmark of our highest quality results for truly intelligent AI. A highly trained workforce, skilled within any given platform, with the ability to easily shift and adjust as project needs require. Customized delivery schedules to meet every need coupled with training and staffing flexibility to pivot based on business need and turnaround time.

Adoption of deep learning has gained a lot of traction during the last two or three years across a wide variety of use cases and has become a top area of interest for many enterprises around the world. Yet, these enterprises still need to determine how best to spend their investment to yield meaningful results for their business. Once an organization has identified the most advantageous use case with which to begin, it is important for CIOs to consider a thoroughly deliberated architectural design. On the one hand, the toolchain for deep learning environments is diverse. There are a wide variety of development toolkits, frameworks and libraries from which to choose. Even the choice of hardware to run the deep learning workload can have a significant impact on an organization's results.

Games have become one of most efficient vehicles for evaluating artificial intelligence(AI) algorithms. For decades, games have built complex competition, collaboration, planning and strategic dynamics that are a reflection of the most sophisticated tasks that AI agents face in the real world. From Chess, to Go to StarCraft, games have become a great lab to evaluate the capabilities of AI agents in a safe and responsible manner. However, most of those great milestones started with agents that were trained on the rules of the game. There is a complementary subset of scenarios in which agents are presented with a new environment without prior knowledge of its dynamics.

Recently, I watched a video https://www.youtube.com/watch?v JPBz7-UCqRo) from my friend Eric Ma on the fundamentals of deep learning. To teach deep learning, he breaks it into 3 key ingredients: model, loss function, and optimization routine. Throughout the tutorial, he uses an automatic differentiation toolbox. However, I find it deeply satisfying to do the derivatives myself (at least for simple cases). Today, I thought I would build a 2-layer neural network from scratch following Eric's approach but with algebraic derivatives (from Andrew Ng's Coursera class), and then implement it again using Keras (a deep learning framework).

Discouraging Words from Machines Impair Human Game Play A new CMU study shows that people who played a game with a humanoid robot known as Pepper performed worse when the robot discouraged them and better when it encouraged them. "This is one of the first studies of human-robot interaction in an environment where they are not cooperating," said co-author Fei Fang, an assistant professor in the Institute for Software Research. Bot Can Beat Humans in Multiplayer Hidden-Role Games MIT researchers have developed a bot, DeepRole, equipped with artificial intelligence that can beat human players in tricky online multiplayer games where player roles and motives are kept secret. At the Conference on Neural Information Processing Systems next month, the researchers will present DeepRole. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model In this work, researchers present the MuZero algorithm which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics. The Deep Learning Revolution and Its Implications for Computer Architecture and Chip Design This paper is a companion paper to a keynote talk at the 2020 International Solid-State Circuits Conference (ISSCC) discussing some of the advances in machine learning, and their implications on the kinds of computational devices we need to build, especially in the post-Moore's Law-era.

Gilbert Strang is a professor of mathematics at MIT and perhaps one of the most famous and impactful teachers of math in the world. His MIT OpenCourseWare lectures on linear algebra have been viewed millions of times. This conversation is part of the Artificial Intelligence podcast.