This research suggests an add-on to empower Google Forms to be an automatic machine for generating multiple-choice questions (MCQs) used in online assessments. In this paper, we elaborate an add-on design mainly comprising question-formulating software and data storage. The algorithm as an intellectual mechanism of this software can produce MCQs at an analytical level. In an experiment, we found the MCQs could assess levels of students' knowledge comparably with those generated by human experts. This add-on can be applied generally to formulate MCQs for any rational concepts. With no effort from an instructor at runtime, the add-on can transform a few data instances describing rational concepts to be variety sets of MCQs.

Multicomponent problems are hard to solve as each component has the potential to influence the feasibility as well as the quality of the other components [4]. Among the studied multi-component problems, vehicle routing problems with loading constraints [15] appear to be very frequently investigated. In these problems, tour are to be created for vehicles while constraints and aims of specific loading policies must be taken into account. One of these problems is the Traveling Thief Problem (TTP), which combines two classic well-known and well-studied problems: the Knapsack Problem (KP) and the Traveling Salesman Problem (TSP). The TTP was proposed in 2013 by Bonyadi et al. [3] in order to provide an academic abstraction of multi-component problems for the scientific community. In the TTP, a thief travels across all cities (TSP component) and steals items along the way (KP component).

With the rapid development of artificial intelligence, conversational bots have became prevalent in mainstream E-commerce platforms, which can provide convenient customer service timely. To satisfy the user, the conversational bots need to understand the user's intention, detect the user's emotion, and extract the key entities from the conversational utterances. However, understanding dialogues is regarded as a very challenging task. Different from common language understanding, utterances in dialogues appear alternately from different roles and are usually organized as hierarchical structures. To facilitate the understanding of dialogues, in this paper, we propose a novel contextual dialogue encoder (i.e. DialogueBERT) based on the popular pre-trained language model BERT. Five self-supervised learning pre-training tasks are devised for learning the particularity of dialouge utterances. Four different input embeddings are integrated to catch the relationship between utterances, including turn embedding, role embedding, token embedding and position embedding. DialogueBERT was pre-trained with 70 million dialogues in real scenario, and then fine-tuned in three different downstream dialogue understanding tasks. Experimental results show that DialogueBERT achieves exciting results with 88.63% accuracy for intent recognition, 94.25% accuracy for emotion recognition and 97.04% F1 score for named entity recognition, which outperforms several strong baselines by a large margin.

Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we need to provide formal guarantees on the safety, security, correctness, or robustness of neural networks. This book covers foundational ideas from formal verification and their adaptation to reasoning about neural networks and deep learning.

Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents. However, the generalization still remains a big challenge as the agents depend critically on the complexity and variety of training tasks. In this paper, we address this problem by introducing a hierarchical framework built upon the knowledge graph-based RL agent. In the high level, a meta-policy is executed to decompose the whole game into a set of subtasks specified by textual goals, and select one of them based on the KG. Then a sub-policy in the low level is executed to conduct goal-conditioned reinforcement learning. We carry out experiments on games with various difficulty levels and show that the proposed method enjoys favorable generalizability.

In this paper, we proposed a novel mutual consistency network (MC-Net+) to effectively exploit the unlabeled hard regions for semi-supervised medical image segmentation. The MC-Net+ model is motivated by the observation that deep models trained with limited annotations are prone to output highly uncertain and easily mis-classified predictions in the ambiguous regions (e.g. adhesive edges or thin branches) for the image segmentation task. Leveraging these region-level challenging samples can make the semi-supervised segmentation model training more effective. Therefore, our proposed MC-Net+ model consists of two new designs. First, the model contains one shared encoder and multiple sightly different decoders (i.e. using different up-sampling strategies). The statistical discrepancy of multiple decoders' outputs is computed to denote the model's uncertainty, which indicates the unlabeled hard regions. Second, a new mutual consistency constraint is enforced between one decoder's probability output and other decoders' soft pseudo labels. In this way, we minimize the model's uncertainty during training and force the model to generate invariant and low-entropy results in such challenging areas of unlabeled data, in order to learn a generalized feature representation. We compared the segmentation results of the MC-Net+ with five state-of-the-art semi-supervised approaches on three public medical datasets. Extension experiments with two common semi-supervised settings demonstrate the superior performance of our model over other existing methods, which sets a new state of the art for semi-supervised medical image segmentation.

The recent advancements in artificial intelligence (AI) combined with the extensive amount of data generated by today's clinical systems, has led to the development of imaging AI solutions across the whole value chain of medical imaging, including image reconstruction, medical image segmentation, image-based diagnosis and treatment planning. Notwithstanding the successes and future potential of AI in medical imaging, many stakeholders are concerned of the potential risks and ethical implications of imaging AI solutions, which are perceived as complex, opaque, and difficult to comprehend, utilise, and trust in critical clinical applications. Despite these concerns and risks, there are currently no concrete guidelines and best practices for guiding future AI developments in medical imaging towards increased trust, safety and adoption. To bridge this gap, this paper introduces a careful selection of guiding principles drawn from the accumulated experiences, consensus, and best practices from five large European projects on AI in Health Imaging. These guiding principles are named FUTURE-AI and its building blocks consist of (i) Fairness, (ii) Universality, (iii) Traceability, (iv) Usability, (v) Robustness and (vi) Explainability. In a step-by-step approach, these guidelines are further translated into a framework of concrete recommendations for specifying, developing, evaluating, and deploying technically, clinically and ethically trustworthy AI solutions into clinical practice.

Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech induced multimodal behaviors to generate a meaningful representation of the conversation. In this work, we propose to dissect SLU into three representative properties:conversational (disfluency, pause, overtalk), channel (speaker-type, turn-tasks) and ASR (insertion, deletion,substitution). We probe BERT based language models (BERT, RoBERTa) trained on spoken transcripts to investigate its ability to understand multifarious properties in absence of any speech cues. Empirical results indicate that LM is surprisingly good at capturing conversational properties such as pause prediction and overtalk detection from lexical tokens. On the downsides, the LM scores low on turn-tasks and ASR errors predictions. Additionally, pre-training the LM on spoken transcripts restrain its linguistic understanding. Finally, we establish the efficacy and transferability of the mentioned properties on two benchmark datasets: Switchboard Dialog Act and Disfluency datasets.

Classification of time series signals has become an important construct and has many practical applications. With existing classifiers we may be able to accurately classify signals, however that accuracy may decline if using a reduced number of attributes. Transforming the data then undertaking reduction in dimensionality may improve the quality of the data analysis, decrease time required for classification and simplify models. We propose an approach, which chooses suitable wavelets to transform the data, then combines the output from these transforms to construct a dataset to then apply ensemble classifiers to. We demonstrate this on different data sets, across different classifiers and use differing evaluation methods. Our experimental results demonstrate the effectiveness of the proposed technique, compared to the approaches that use either raw signal data or a single wavelet transform.

The Association for the Advancement of Artificial Intelligence's 2020 Fall Symposium Series was held virtually from November 11-14, 2020, and was collocated with three symposia postponed from March 2020 due to the COVID-19 Pandemic. There were five symposia in the fall program: AI for Social Good, Artificial Intelligence in Government and Public Sector, Conceptual Abstraction and Analogy in Natural and Artificial Intelligence, Physics-Guided AI to Accelerate Scientific Discovery, and Trust and Explainability in Artificial Intelligence for Human-Robot Interaction. Additionally, there were three symposia delayed from spring: AI Welcomes Systems Engineering: Towards the Science of Interdependence for Autonomous Human-Machine Teams, Deep Models and Artificial Intelligence for Defense Applications: Potentials, Theories, Practices, Tools, and Risks, and Towards Responsible AI in Surveillance, Media, and Security through Licensing. Recent developments in big data and computational power are revolutionizing several domains, opening up new opportunities and challenges. In this symposium, we highlighted two specific themes, namely humanitarian relief, and healthcare, where AI could be used for social good to achieve the United Nations (UN) sustainable development goals (SDGs) in those areas, which touch every aspect of human, social, and economic development. The talks at the symposium were focused on identifying the critical needs and pathways for responsible AI solutions to achieve SDGs, which demand holistic thinking on optimizing the trade-off between automation benefits and their potential side-effects, especially in a year that has upended societies globally due to the COVID-19 pandemic. Riding on the success of the AI for Social Good symposium that was held in Washington, DC, in November 2019, we organized the 2020 version of the symposium.