Total: 14
This “blue sky” paper argues that future conversational systems that can engage in multiparty, collaborative dialogues will require a more fundamental approach than existing technology. This paper identifies significant limitations of the state of the art, and argues that our returning to the plan-based approach to dialogue will provide a stronger foundation. Finally, I suggest a research strategy that couples neural network-based semantic parsing with plan-based reasoning in order to build a collaborative dialogue manager.
Many challenging problems of scientific, technological, and societal significance require us to aggregate information supplied by multiple agents into a single piece of information of the same type—the collective information representing the stance of the group as a whole. Examples include expressive forms of voting and democratic decision making (where citizens supply information regarding their preferences), peer evaluation (where participants supply information in the form of assessments of their peers), and crowdsourcing (where volunteers supply information by annotating data). In this position paper, I outline the challenge of modelling, handling, and analysing all of these diverse instances of collective information using a common methodology. Addressing this challenge will facilitate a transfer of knowledge between different application domains, thereby enabling progress in all of them.
As is evidenced by the associated AI, Ethics and Society conference, we now take as given the need for ethics education in the AI and general CS curricula. The anticipated surge in AI ethics education will force the field to reckon with delineating and then evaluating learner outcomes to determine what is working and improve what is not. We argue for a more descriptive than normative focus of this ethics education, and propose the development of assessments that can measure descriptive ethical thinking about AI. Such an assessment tool for measuring ethical reasoning capacity in CS contexts must be designed to produce reliable scores for which there is established validity evidence concerning their interpretation and use.
Modern software systems are highly complex and often have multiple dependencies on external parts such as other processes or services. This poses new challenges and exacerbate existing challenges in different aspects of software Quality Assurance (QA) including testing, debugging and repair. The goal of this talk is to present a novel AI paradigm for software QA (AI4QA). A quality assessment AI agent uses machine-learning techniques to predict where coding errors are likely to occur. Then a test generation AI agent considers the error predictions to direct automated test generation. Then a test execution AI agent executes tests, that are passed to the root-cause analysis AI agent, which applies automatic debugging algorithms. The candidate root causes are passed to a code repair AI agent that tries to create a patch for correcting the isolated error.
Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: Explainable decisions in Multi-Agent Environments (xMASE). We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI systems' decisions in multi-agent environments.
In this paper, I pose a new research challenge – to develop intelligent agents that exhibit radical autonomy by responding to sudden, long-term changes in their environments. I illustrate this idea with examples, identify abilities that support it, and argue that, although each ability has been studied in isolation, they have not been combined into integrated systems. In addition, I propose a framework for characterizing environments in which goal-directed physical agents operate, along with specifying the ways in which those environments can change over time. In closing, I outline some approaches to the empirical study of such open-world learning.
One of the hallmarks of the human intelligence is the ability to learn continuously, accumulate the knowledge learned in the past and use the knowledge to help learn more and learn better. It is hard to imagine a truly intelligent system without this capability. This type of learning differs significantly than the classic machine learning (ML) paradigm of isolated single-task learning. Although there is already research on learning a sequence of tasks incrementally under the names of lifelong learning or continual learning, they still follow the traditional two-phase separate training and testing paradigm in learning each task. The tasks are also given by the user. This paper adds on-the-job learning to the mix to emphasize the need to learn during application (thus online) after the model has been deployed, which traditional ML cannot do. It aims to leverage the learned knowledge to discover new tasks, interact with humans and the environment, make inferences, and incrementally learn the new tasks on the fly during applications in a self-supervised and interactive manner. This is analogous to human on-the-job learning after formal training. We use chatbots and self-driving cars as examples to discuss the need, some initial work, and key challenges and opportunities in building this capability.
Recent years have seen significant advances in machine perception, which have enabled AI systems to become grounded in the world. While AI systems can now "read" and "see", they still cannot read between the lines and see through the lens, unlike humans. We propose the novel task of hidden message and intention identification: given some perceptual input (i.e., a text, an image), the goal is to produce a short description of the message the input transmits and the hidden intention of its author, if any. Not only will a solution to this task enable machine perception technologies to reach the next level of complexity, but it will be an important step towards addressing a task that has recently received a lot of public attention, political manipulation in social media.
We survey a burgeoning and promising new research area that considers the online nature of many practical fair division problems. We identify wide variety of such online fair division problems, as well as discuss new mechanisms and normative properties that apply to this online setting. The online nature of such fair division problems provides both opportunities and challenges such as the possibility to develop new online mechanisms as well as the difficulty of dealing with an uncertain future.
Fairness is becoming an increasingly important concern when designing markets, allocation procedures, and computer systems. I survey some recent developments in the field of multi-agent fair allocation.
It is widely known that AI planning and model checking are closely related. Compilations have been devised between various pairs of language fragments. What has barely been voiced yet, though, is the idea to let go of one's own modeling language, and use one from the other area instead. We advocate that idea here – to use automata-network languages from model checking instead of PDDL – motivated by modeling difficulties relating to planning agents surrounded by exogenous agents in complex environments. One could, of course, address this by designing additional extended planning languages. But one can also leverage decades of work on modeling in the formal methods community, creating potential for deep synergy and integration with their techniques as a side effect. We believe there's a case to be made for the latter, as one modeling alternative in planning among others.
Machine learning has become prevalent across a wide variety of applications. Unfortunately, machine learning has also shown to be susceptible to deception, leading to errors, and even fatal failures. This circumstance calls into question the widespread use of machine learning, especially in safety-critical applications, unless we are able to assure its correctness and trustworthiness properties. Software verification and testing are established technique for assuring such properties, for example by detecting errors. However, software testing challenges for machine learning are vast and profuse - yet critical to address. This summary talk discusses the current state-of-the-art of software testing for machine learning. More specifically, it discusses six key challenge areas for software testing of machine learning systems, examines current approaches to these challenges and highlights their limitations. The paper provides a research agenda with elaborated directions for making progress toward advancing the state-of-the-art on testing of machine learning.
Face recognition algorithms have demonstrated very high recognition performance, suggesting suitability for real world applications. Despite the enhanced accuracies, robustness of these algorithms against attacks and bias has been challenged. This paper summarizes different ways in which the robustness of a face recognition algorithm is challenged, which can severely affect its intended working. Different types of attacks such as physical presentation attacks, disguise/makeup, digital adversarial attacks, and morphing/tampering using GANs have been discussed. We also present a discussion on the effect of bias on face recognition models and showcase that factors such as age and gender variations affect the performance of modern algorithms. The paper also presents the potential reasons for these challenges and some of the future research directions for increasing the robustness of face recognition models.
Constraint Programming is a powerful paradigm to model and solve combinatorial problems. While there are many kinds of constraints, the table constraint (also called a CSP) is perhaps the most significant—being the most well-studied and has the ability to encode any other constraints defined on finite variables. Thus, designing efficient filtering algorithms on table constraints has attracted significant research efforts. In turn, there have been great improvements in efficiency over time with the evolution and development of AC and GAC algorithms. In this paper, we survey the existing filtering algorithms for table constraint focusing on historically important ideas and recent successful techniques shown to be effective.