In this work, we seek to finetune a weakly-supervised expert-guided Deep Neural Network (DNN) for the purpose of determining political affiliations. In this context, stance detection is used for determining political affiliation or ideology which is framed in the form of relative proximities between entities in a low-dimensional space. An attention-based mechanism is used to provide model interpretability. A Deep Neural Network for Natural Language Understanding (NLU) using static and contextual embeddings is trained and evaluated. Various techniques to visualize the projections generated from the network are evaluated for visualization efficiency. An overview of the pipeline from data ingestion, processing and generation of visualization is given here. A web-based framework created to faciliate this interaction and exploration is presented here. Preliminary results of this study are summarized and future work is outlined.

Semantic role labeling (SRL) is a task to recognize all the predicate-argument pairs of a sentence, which has been in a performance improvement bottleneck after a series of latest works were presented. This paper proposes a novel syntax-agnostic SRL model enhanced by the proposed associated memory network (AMN), which makes use of inter-sentence attention of label-known associated sentences as a kind of memory to further enhance dependency-based SRL. In detail, we use sentences and their labels from train dataset as an associated memory cue to help label the target sentence. Furthermore, we compare several associated sentences selecting strategies and label merging methods in AMN to find and utilize the label of associated sentences while attending them. By leveraging the attentive memory from known training data, Our full model reaches state-of-the-art on CoNLL-2009 benchmark datasets for syntax-agnostic setting, showing a new effective research line of SRL enhancement other than exploiting external resources such as well pre-trained language models. 1 Introduction Semantic role labeling (SRL) is a task to recognize all the predicate-argument pairs of a given sentence and its predicates. It is a shallow semantic parsing task, which has been widely used in a series of natural language processing (NLP) tasks, such as information extraction (Liu et al., 2016) and question answering (Abujabal et al., 2017). Generally, SRL is decomposed into four classification subtasks in pipeline systems, consisting of Corresponding author.

We present a novel method for training a social robot to generate backchannels during human-robot interaction. We address the problem within an off-policy reinforcement learning framework, and show how a robot may learn to produce non-verbal backchannels like laughs, when trained to maximize the engagement and attention of the user. A major contribution of this work is the formulation of the problem as a Markov decision process (MDP) with states defined by the speech activity of the user and rewards generated by quantified engagement levels. The problem that we address falls into the class of applications where unlimited interaction with the environment is not possible (our environment being a human) because it may be time-consuming, costly, impracticable or even dangerous in case a bad policy is executed. Therefore, we introduce deep Q-network (DQN) in a batch reinforcement learning framework, where an optimal policy is learned from a batch data collected using a more controlled policy. We suggest the use of human-to-human dyadic interaction datasets as a batch of trajectories to train an agent for engaging interactions. Our experiments demonstrate the potential of our method to train a robot for engaging behaviors in an offline manner.

The EmbodiedQA is a task of training an embodied agent by intelligently navigating in a simulated environment and gathering visual information to answer questions. Existing approaches fail to explicitly model the mental imagery function of the agent, while the mental imagery is crucial to embodied cognition, and has a close relation to many high-level meta-skills such as generalization and interpretation. In this paper, we propose a novel Mental Imagery eNhanceD (MIND) module for the embodied agent, as well as a relevant deep reinforcement framework for training. The MIND module can not only model the dynamics of the environment (e.g. 'what might happen if the agent passes through a door') but also help the agent to create a better understanding of the environment (e.g. 'The refrigerator is usually in the kitchen'). Such knowledge makes the agent a faster and better learner in locating a feasible policy with only a few trails. Furthermore, the MIND module can generate mental images that are treated as short-term subgoals by our proposed deep reinforcement framework. These mental images facilitate policy learning since short-term subgoals are easy to achieve and reusable. This yields better planning efficiency than other algorithms that learn a policy directly from primitive actions. Finally, the mental images visualize the agent's intentions in a way that human can understand, and this endows our agent's actions with more interpretability. The experimental results and further analysis prove that the agent with the MIND module is superior to its counterparts not only in EQA performance but in many other aspects such as route planning, behavioral interpretation, and the ability to generalize from a few examples.

The Leidos' Innovation Center has a vacancy for an Artificial Intelligence Software Developer to join our team in Beavercreek, OH to provide support for autonomous system development for our Air Force customer. The successful candidate will work with our team and customer to plan, prepare for, and execute advanced research in the areas of autonomy, sensor fusion, and exploitation, leveraging machine learning and artificial intelligence techniques.

Artificial Intelligence (AI) has incredible potential to improve lives and create a better world, but the stakes are high and the consequences will be disastrous if the technology is misused. Those are the findings of a new "horizon scanning" report by the Australian Council of Learned Academies (ACOLA), titled The Effective and Ethical Development of Artificial Intelligence – An Opportunity to Improve our Wellbeing. "Horizon scanning" is a way for governments and decision-makers to "look at the future challenges and opportunities that the technologies pose", UNSW Professor of Artificial Intelligence Toby Walsh, co-chair of the report's expert working group, said. The report draws on research and expertise from a wide range of disciplines including science, medicine, economics, philosophy and law. At its best, AI has the power to enhance Australia's wellbeing, lift the economy, improve environmental sustainability and create a more equitable, inclusive and fair society, the report said.

A student begins a course of study with a short diagnostic test to assess how well she understands key concepts. If she correctly answers an early question, the system will assume she knows related concepts and skip ahead. Within 10 questions, the system has a rough sketch of what she needs to work on, and uses it to build a curriculum. As she studies, the system updates its model of her understanding and adjusts the curriculum accordingly. As more students use the system, it spots previously unrealized connections between concepts.

A paper posted online this month has settled a nearly 30-year-old conjecture about the structure of the fundamental building blocks of computer circuits. This "sensitivity" conjecture has stumped many of the most prominent computer scientists over the years, yet the new proof is so simple that one researcher summed it up in a single tweet. Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research develop ments and trends in mathe matics and the physical and life sciences. "This conjecture has stood as one of the most frustrating and embarrassing open problems in all of combinatorics and theoretical computer science," wrote Scott Aaronson of the University of Texas, Austin, in a blog post. "The list of people who tried to solve it and failed is like a who's who of discrete math and theoretical computer science," he added in an email.

In 2015, car-and-rocket man Elon Musk joined with influential startup backer Sam Altman to put artificial intelligence on a new, more open course. They cofounded a research institute called OpenAI to make new AI discoveries and give them away for the common good. Now, the institute's researchers are sufficiently worried by something they built that they won't release it to the public. The AI system that gave its creators pause was designed to learn the patterns of language. It does that very well--scoring better on some reading-comprehension tests than any other automated system.

The United States' technological sophistication has long supported its military predominance. In the 1990s, the U.S. military started to hold an uncontested advantage over its adversaries in the technologies of information-age warfare--from stealth and precision weapons to high-tech sensors and command-and-control systems. Those technologies remain critical to its forces today. For years, China has closely watched the United States' progress, developing asymmetric tools--including space, cyber, and electronic capabilities--that exploit the U.S. military's vulnerabilities. Today, however, the Chinese People's Liberation Army (PLA) is pursuing innovations in many of the same emerging technologies that the U.S. military has itself prioritized. Artificial intelligence is chief among these.