SemEval task 4 aims to find a proper option from multiple candidates to resolve the task of machine reading comprehension. Most existing approaches propose to concat question and option together to form a context-aware model. However, we argue that straightforward concatenation can only provide a coarse-grained context for the MRC task, ignoring the specific positions of the option relative to the question. In this paper, we propose a novel MRC model by filling options into the question to produce a fine-grained context (defined as summary) which can better reveal the relationship between option and question. We conduct a series of experiments on the given dataset, and the results show that our approach outperforms other counterparts to a large extent.

Classification and identification of amino acids in aqueous solutions is important in the study of biomacromolecules. Laser Induced Breakdown Spectroscopy (LIBS) uses high energy laser-pulses for ablation of chemical compounds whose radiated spectra are captured and recorded to reveal molecular structure. Spectral peaks and noise from LIBS are impacted by experimental protocols. Current methods for LIBS spectral analysis achieves promising results using PCA, a linear method. It is well-known that the underlying physical processes behind LIBS are highly nonlinear. Our work set out to understand the impact of LIBS spectra on suitable neighborhood size over which to consider pattern phenomena, if nonlinear methods capture pattern phenomena with increased efficacy, and how they improve classification and identification of compounds. We analyzed four amino acids, polysaccharide, and a control group, water. We developed an information theoretic method for measurement of LIBS energy spectra, implemented manifold methods for nonlinear dimensionality reduction, and found while clustering results were not statistically significantly different, nonlinear methods lead to increased classification accuracy. Moreover, our approach uncovered the contribution of micro-wells (experimental protocol) in LIBS spectra. To the best of our knowledge, ours is the first application of Manifold methods to LIBS amino-acid analysis in the research literature.

Manifold learning is used for dimensionality reduction, with the goal of finding a projection subspace to increase and decrease the inter- and intraclass variances, respectively. However, a bottleneck for subspace learning methods often arises from the high dimensionality of datasets. In this paper, a hierarchical approach is proposed to scale subspace learning methods, with the goal of improving classification in large datasets by a range of 3% to 10%. Different combinations of methods are studied. We assess the proposed method on five publicly available large datasets, for different eigen-value based subspace learning methods such as linear discriminant analysis, principal component analysis, generalized discriminant analysis, and reconstruction independent component analysis. To further examine the effect of the proposed method on various classification methods, we fed the generated result to linear discriminant analysis, quadratic linear analysis, k-nearest neighbor, and random forest classifiers. The resulting classification accuracies are compared to show the effectiveness of the hierarchical approach, reporting results of an average of 5% increase in classification accuracy.

A test is adaptive when its sequence and number of questions is dynamically tuned on the basis of the estimated skills of the taker. Graphical models, such as Bayesian networks, are used for adaptive tests as they allow to model the uncertainty about the questions and the skills in an explainable fashion, especially when coping with multiple skills. A better elicitation of the uncertainty in the question/skills relations can be achieved by interval probabilities. This turns the model into a credal network, thus making more challenging the inferential complexity of the queries required to select questions. This is especially the case for the information theoretic quantities used as scores to drive the adaptive mechanism. We present an alternative family of scores, based on the mode of the posterior probabilities, and hence easier to explain. This makes considerably simpler the evaluation in the credal case, without significantly affecting the quality of the adaptive process. Numerical tests on synthetic and real-world data are used to support this claim.

Intelligent behaviour in the physical world exhibits structure at multiple spatial and temporal scales. Although movements are ultimately executed at the level of instantaneous muscle tensions or joint torques, they must be selected to serve goals defined on much longer timescales, and in terms of relations that extend far beyond the body itself, ultimately involving coordination with other agents. Recent research in artificial intelligence has shown the promise of learning-based approaches to the respective problems of complex movement, longer-term planning and multi-agent coordination. However, there is limited research aimed at their integration. We study this problem by training teams of physically simulated humanoid avatars to play football in a realistic virtual environment. We develop a method that combines imitation learning, single- and multi-agent reinforcement learning and population-based training, and makes use of transferable representations of behaviour for decision making at different levels of abstraction. In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds. We investigate the emergence of behaviours at different levels of abstraction, as well as the representations that underlie these behaviours using several analysis techniques, including statistics from real-world sports analytics. Our work constitutes a complete demonstration of integrated decision-making at multiple scales in a physically embodied multi-agent setting. See project video at https://youtu.be/KHMwq9pv7mg.

Autonomous discovery and direct instruction are two extreme sources of learning in children, but educational sciences have shown that intermediate approaches such as assisted discovery or guided play resulted in better acquisition of skills. When turning to Artificial Intelligence, the above dichotomy is translated into the distinction between autonomous agents which learn in isolation and interactive learning agents which can be taught by social partners but generally lack autonomy. In between should stand teachable autonomous agents: agents learning from both internal and teaching signals to benefit from the higher efficiency of assisted discovery. Such agents could learn on their own in the real world, but non-expert users could drive their learning behavior towards their expectations. More fundamentally, combining both capabilities might also be a key step towards general intelligence. In this paper we elucidate obstacles along this research line. First, we build on a seminal work of Bruner to extract relevant features of the assisted discovery processes. Second, we describe current research on autotelic agents, i.e. agents equipped with forms of intrinsic motivations that enable them to represent, self-generate and pursue their own goals. We argue that autotelic capabilities are paving the way towards teachable and autonomous agents. Finally, we adopt a social learning perspective on tutoring interactions and we highlight some components that are currently missing to autotelic agents before they can be taught by ordinary people using natural pedagogy, and we provide a list of specific research questions that emerge from this perspective.

This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels. Previous research on this task mainly defines the difficulty of a question as whether it can be correctly answered by a Question Answering (QA) system, lacking interpretability and controllability. In our work, we redefine question difficulty as the number of inference steps required to answer it and argue that Question Generation (QG) systems should have stronger control over the logic of generated questions. To this end, we propose a novel framework that progressively increases question difficulty through step-bystep rewriting under the guidance of an extracted reasoning chain. A dataset is automatically constructed to facilitate the research, on Figure 1: An example of generating a complex question which extensive experiments are conducted to through step-by-step rewriting based on the reasoning test the performance of our method.

In partially observable reinforcement learning, offline training gives access to latent information which is not available during online training and/or execution, such as the system state. Asymmetric actor-critic methods exploit such information by training a history-based policy via a state-based critic. However, many asymmetric methods lack theoretical foundation, and are only evaluated on limited domains. We examine the theory of asymmetric actor-critic methods which use state-based critics, and expose fundamental issues which undermine the validity of a common variant, and its ability to address high partial observability. We propose an unbiased asymmetric actor-critic variant which is able to exploit state information while remaining theoretically sound, maintaining the validity of the policy gradient theorem, and introducing no bias and relatively low variance into the training process. An empirical evaluation performed on domains which exhibit significant partial observability confirms our analysis, and shows the unbiased asymmetric actor-critic converges to better policies and/or faster than symmetric actor-critic and standard asymmetric actor-critic baselines.

This forms the basis for everything else. The central object in Numpy is the Numpy array, on which you can do various operations. We know that the matrix and arrays play an important role in numerical computation and data analysis. Pandas and other ML or AI tools need tabular or array-like data to work efficiently, so using NumPy in Pandas and ML packages can reduce the time and improve the performance of the data computation. NumPy based arrays are 10 to 100 times (even more than 100 times) faster than the Python Lists, hence if you are planning to work as a Data Analyst or Data Scientist or Big Data Engineer with Python, then you must be familiar with the NumPy as it offers a more convenient way to work with Matrix-like objects like Nd-arrays.

Quantum machine learning is the fusion of quantum computing and artificial intelligence that will alter the future. It's an area dedicated to developing quantum algorithms for machine learning tasks. In the coming years, quantum machine learning is expected to be a possible application of quantum computers. Many quantum machine learning algorithms have been suggested to help quantum computers accelerate classical machine learning. Deep learning, on the other hand, has proven to be extremely effective in solving real-world problems.