Memorizing All for Implicit Discourse Relation Recognition

Implicit discourse relation recognition is a challenging task due to the absence of the necessary informative clues from explicit connectives. An implicit discourse relation recognizer has to carefully tackle the semantic similarity of sentence pairs and the severe data sparsity issue. In this article, we learn token embeddings to encode the structure of a sentence from a dependency point of view in their representations and use them to initialize a baseline model to make it really strong. Then, we propose a novel memory component to tackle the data sparsity issue by allowing the model to master the entire training set, which helps in achieving further performance improvement. The memory mechanism adequately memorizes information by pairing representations and discourse relations of all training instances, thus filling the slot of the data-hungry issue in the current implicit discourse relation recognizer. The proposed memory component, if attached with any suitable baseline, can help in performance enhancement. The experiments show that our full model with memorizing the entire training data provides excellent results on PDTB and CDTB datasets, outperforming the baselines by a fair margin.

Computer Vision for Autonomous UAV Flight Safety: An Overview and a Vision-based Safe Landing Pipeline Example

Recent years have seen an unprecedented spread of Unmanned Aerial Vehicles (UAVs, or “drones”), which are highly useful for both civilian and military applications. Flight safety is a crucial issue in UAV navigation, having to ensure accurate compliance with recently legislated rules and regulations. The emerging use of autonomous drones and UAV swarms raises additional issues, making it necessary to transfuse safety- and regulations-awareness to relevant algorithms and architectures. Computer vision plays a pivotal role in such autonomous functionalities. Although the main aspects of autonomous UAV technologies (e.g., path planning, navigation control, landing control, mapping and localization, target detection/tracking) are already mature and well-covered, ensuring safe flying in the vicinity of crowds, avoidance of passing over persons, or guaranteed emergency landing capabilities in case of malfunctions, are generally treated as an afterthought when designing autonomous UAV platforms for unstructured environments. This fact is reflected in the fragmentary coverage of the above issues in current literature. This overview attempts to remedy this situation, from the point of view of computer vision. It examines the field from multiple aspects, including regulations across the world and relevant current technologies. Finally, since very few attempts have been made so far towards a complete UAV safety flight and landing pipeline, an example computer vision-based UAV flight safety pipeline is introduced, taking into account all issues present in current autonomous drones. The content is relevant to any kind of autonomous drone flight (e.g., for movie/TV production, news-gathering, search and rescue, surveillance, inspection, mapping, wildlife monitoring, crowd monitoring/management), making this a topic of broad interest.

Gotta CAPTCHA ’Em All: A Survey of 20 Years of the Human-or-computer Dilemma

A recent study has found that malicious bots generated nearly a quarter of overall website traffic in 2019 [102]. These malicious bots perform activities such as price and content scraping, account creation and takeover, credit card fraud, denial of service, and so on. Thus, they represent a serious threat to all businesses in general, but are especially troublesome for e-commerce, travel, and financial services. One of the most common defense mechanisms against bots abusing online services is the introduction of Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA), so it is extremely important to understand which CAPTCHA schemes have been designed and their actual effectiveness against the ever-evolving bots. To this end, this work provides an overview of the current state-of-the-art in the field of CAPTCHA schemes and defines a new classification that includes all the emerging schemes. In addition, for each identified CAPTCHA category, the most successful attack methods are summarized by also describing how CAPTCHA schemes evolved to resist bot attacks, and discussing the limitations of different CAPTCHA schemes from the security, usability, and compatibility point of view. Finally, an assessment of the open issues, challenges, and opportunities for further study is provided, paving the road toward the design of the next-generation secure and user-friendly CAPTCHA schemes.

Classification of Arabic fricative consonants according to their places of articulation

<span>Many technology systems have used voice recognition applications to transcribe a speaker’s speech into text that can be used by these systems. One of the most complex tasks in speech identification is to know, which acoustic cues will be used to classify sounds. This study presents an approach for characterizing Arabic fricative consonants in two groups (sibilant and non-sibilant). From an acoustic point of view, our approach is based on the analysis of the energy distribution, in frequency bands, in a syllable of the consonant-vowel type. From a practical point of view, our technique has been implemented, in the MATLAB software, and tested on a corpus built in our laboratory. The results obtained show that the percentage energy distribution in a speech signal is a very powerful parameter in the classification of Arabic fricatives. We obtained an accuracy of 92% for non-sibilant consonants /f, χ, ɣ, ʕ, ћ, and h/, 84% for sibilants /s, sҁ, z, Ӡ and ∫/, and 89% for the whole classification rate. In comparison to other algorithms based on neural networks and support vector machines (SVM), our classification system was able to provide a higher classification rate.</span>

A Vexing Question in Motor Control: The Degrees of Freedom Problem

The human “marionette” is extremely complex and multi-articulated: anatomical redundancy (in terms of Degrees of Freedom: DoFs), kinematic redundancy (movements can have different trajectories, velocities, and accelerations and yet achieve the same goal, according to the principle of Motor Equivalence), and neurophysiological redundancy (many more muscles than DoFs and multiple motor units for each muscle). Although it is quite obvious that such abundance is not noxious at all because, in contrast, it is instrumental for motor learning, allowing the nervous system to “explore” the space of feasible actions before settling on an elegant and possibly optimal solution, the crucial question then boils down to figure out how the nervous system “chooses/selects/recruits/modulates” task-dependent subsets of countless assemblies of DoFs as functional motor synergies. Despite this daunting conceptual riddle, human purposive behavior in daily life activities is a proof of concept that solutions can be found easily and quickly by the embodied brain of the human cognitive agent. The point of view suggested in this essay is to frame the question above in the old-fashioned but still seminal observation by Marr and Poggio that cognitive agents should be regarded as Generalized Information Processing Systems (GIPS) and should be investigated according to three nearly independent but complementary levels of analysis: 1) the computational level, 2) the algorithmic level, and 3) the implementation level. In this framework, we attempt to discriminate as well as aggregate the different hypotheses and solutions proposed so far: the optimal control hypothesis, the muscle synergy hypothesis, the equilibrium point hypothesis, or the uncontrolled manifold hypothesis, to mention the most popular ones. The proposed GIPS follows the strategy of factoring out shaping and timing by adopting a force-field based approach (the Passive Motion Paradigm) that is inspired by the Equilibrium Point Hypothesis, extended in such a way to represent covert as well overt actions. In particular, it is shown how this approach can explain spatio-temporal invariances and, at the same time, solve the Degrees of Freedom Problem.

EVIDENTIALITY IN THE TURKIC LANGUAGES: THE TYPOLOGICAL VIEW

В статье рассматриваются особенности выражения категории эвиденциальности в тюркских языках. Выделены значения достоверности, неочевидности и неожиданного обнаружения. Равномерное рассредоточение средств выражения по всем языковым уровням признано основным формальным признаком эвиденциальной системы тюркских языков. В этом смысле тюркские языки контрастируют с языками, в которых большая функциональная нагрузка ложится на лексические средства (как, например, в русском языке). Приводятся краткие сведения еще об одном типе языков по исследуемому признаку: его представляют языки, имеющие парадигму особого наклонения - эвиденциалиса (некоторые уральские). С типологической точки зрения весь представленный в тюркских языках комплекс искомых значений и средств их выражения признан особым типом эвиденциальной системности. The article deals with the features of the expression of the category of evidentiality in the Turkic languages. The values of confidence, non - obviousness, and unexpected detection are highlighted. The uniform distribution of the means of expression across all language levels is recognized as the main formal feature of the evidential system of the Turkic languages. In this sense, the Turkic languages contrast with languages in which a large functional load falls on lexical means (as, for example, in Russian). Brief information is given about another type of language according to the studied feature: it is represented by languages that have a paradigm of a special mood - evidentialis (some Uralic). From the typological point of view, the whole complex of the desired meanings and means of their expression presented in the Turkic languages is recognized as a special type of the evidential system.

Nonlinear Dynamics of a Single-Mode Semiconductor Laser with Long Delayed Optical Feedback: A Modern Experimental Characterization Approach

Semiconductor lasers can exhibit complex dynamical behavior in the presence of external perturbations. Delayed optical feedback, re-injecting part of the emitted light back into the laser cavity, in particular, can destabilize the laser’s emission. We focus on the emission properties of a semiconductor laser subject to such optical feedback, where the delay of the light re-injection is large compared to the relaxation oscillations period. We present an overview of the main dynamical features that emerge in semiconductor lasers subject to delayed optical feedback, emphasizing how to experimentally characterize these features using intensity and high-resolution optical spectra measurements. The characterization of the system requires the experimentalist to be able to simultaneously measure multiple time scales that can be up to six orders of magnitude apart, from the picosecond to the microsecond range. We highlight some experimental observations that are particularly interesting from the fundamental point of view and, moreover, provide opportunities for future photonic applications.

A relational theory of effects and coeffects

Graded modal types systems and coeffects are becoming a standard formalism to deal with context-dependent, usage-sensitive computations, especially when combined with computational effects. From a semantic perspective, effectful and coeffectful languages have been studied mostly by means of denotational semantics and almost nothing has been done from the point of view of relational reasoning. This gap in the literature is quite surprising, since many cornerstone results — such as non-interference , metric preservation , and proof irrelevance — on concrete coeffects are inherently relational. In this paper, we fill this gap by developing a general theory and calculus of program relations for higher-order languages with combined effects and coeffects. The relational calculus builds upon the novel notion of a corelator (or comonadic lax extension ) to handle coeffects relationally. Inside such a calculus, we define three notions of effectful and coeffectful program refinements: contextual approximation , logical preorder , and applicative similarity . These are the first operationally-based notions of program refinement (and, consequently, equivalence) for languages with combined effects and coeffects appearing in the literature. We show that the axiomatics of a corelator (together with the one of a relator) is precisely what is needed to prove all the aforementioned program refinements to be precongruences, this way obtaining compositional relational techniques for reasoning about combined effects and coeffects.