Suchergebnisse

This position paper puts forward machine coaching as a form of interactive machine learning that emphasizes the requirement for humans and machines to externalize their internal reasoning process in a manner that is understandable, at least at a basic level, by the other party. We posit that this mutual understanding leads to a computationally and cognitively lighter interaction, supports the run-time personalization of machines even by non-technically-savvy humans, makes any machine biases explicit and the process of their acquisition transparent, and facilitates the development of AI systems that can, by design, explain and be explained to. Backed by psychological theories of human reasoning and recent technical work, this paper adopts the working hypothesis that argumentation over symbolic rulebased knowledge offers a reasonable common language and semantics that machines and humans can utilize when interacting through machine coaching. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and under Grant Agreement No 823783 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

The Winograd Schema Challenge (WSC), a novel litmus test for machine intelligence, has been proposed to advance the field of AI. Over the last decade, AI researchers have become increasingly interested in this challenge. While a common and trivial task for humans, studies have shown that the WSC is still difficult for current AI systems. Tackling the challenge would likely require access to a sufficiently rich set of Winograd schema examples, which are currently limited in their number and too cumbersome to create completely manually. Towards addressing these limitations, we propose a machine-driven approach for the development of large numbers of schemas. Our empirical evaluation suggests that our developed system, which blends the advantages of Machine Learning and Natural Language Processing, is able to automatically develop Winograd schemas autonomously, or considerably help humans in the development task. ; This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Republic of Cyprus through the Deputy Ministry of Research, Innovation and Digital Policy.

The overwhelming number of events of potential interest to local or national authorities is often in stark contrast to the severely limited resources that authorities can avail for identifying such events. The active engagement of citizens in the identification task is, arguably, a potential solution to this problem, but brings with it a number of other issues that need to be addressed: How are citizens incentivized to participate? How is the veracity of reported events assessed? To what extent can relevant processes be automated? This position paper puts forward an architecture for an integrated platform that couples citizen-sourced reporting with the semi-autonomous use of drones for assessing the veracity of sourced reports, and discusses the multiple facets of such an architecture in relation to typical research questions for autonomous agents and multi-agent systems. ; This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Republic of Cyprus through the Deputy Ministry of Research, Innovation and Digital Policy.

Past work on the task of identifying the geographic focus of news-stories has established that state-of-the-art performance can be achieved by using existing crowdsourced knowledge-bases. In this work we demonstrate that a further refinement of those knowledge-bases through an additional round of crowdsourcing can lead to improved performance on the aforementioned task. Our proposed methodology views existing knowledgebases as collections of arguments in support of particular inferences in terms of the geographic focus of a given news-story. The refinement that we propose is to associate these arguments with weights—computed through crowdsourcing—in terms of how strongly they support their inference. The empirical results that we present establish the superior performance of this approach compared to the one using the original knowledge-base. ; This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Republic of Cyprus through the Deputy Ministry of Research, Innovation and Digital Policy.

The Winograd Schema Challenge—the task of resolving pronouns in certain carefully-constructed sentences —has recently been proposed as a basis for a novel form of CAPTCHAs. Such uses of the task necessitate the availability of a large, and presumably continuously-replenished, collection of available Winograd Schemas, which goes beyond what human experts can reasonably develop by themselves. Towards tackling this issue, we introduce Winventor, the first, to our knowledge, system that attempts to fully automate the development of Winograd Schemas, or at least to considerably help humans in this development task. Beyond describing the system, the paper presents a series of three studies that demonstrate, respectively, Winventor's ability to replicate existingWinograd Schemas from the literature, automatically develop reasonableWinograd Schemas from scratch, and aid humans in developing Winograd Schemas by post-processing the system's suggestions. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and under Grant Agreement No 823783 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

The Winograd Schema Challenge (WSC), the task of resolving pronouns in certain carefully-structured sentences, has received considerable interest in the past few years as an alternative to the Turing Test. In our recent work we demonstrated the plausibility of using commonsense knowledge, automatically acquired from raw text in English Wikipedia, towards computing a metric of hardness for a limited number of Winograd Schemas. In this work we present WinoReg, a new system to compute hardness of Winograd Schemas, by training a Random Forest classier over a rich set of features identied in relevant WSC works in the literature. Our empirical study shows that this new system is considerably faster and more accurate compared to the system proposed in our earlier work, making its use as part of other WSC-based systems feasible. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and under Grant Agreement No 823783 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

The Winograd Schema Challenge, the task of resolving pronouns in certain carefully-structured sentences, has received considerable interest in the past few years as an alternative to the Turing Test. Systems developed to tackle this challenge have typically been evaluated on a small set of hand-crafted collections of sentences, since the development of new sentences by individuals is itself a rather challenging task, requiring care and creativity. In this paper we approach the problem of developing Winograd schemas via the introduction of WinoFlexi, a flexible online crowdsourcing system. Our empirical evaluation of the system's performance suggests that WinoFlexi allows crowdworkers to develop Winograd schemas of quality similar to that of most typical existing collections. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and under Grant Agreement No 823783 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

CAPTCHAs have established themselves as a standard technology to condently distinguish humans from bots. Beyond the typical use for security reasons, CAPTCHAs have helped promote AI research in challenge tasks such as image classication and optical character recognition. It is, therefore, natural to consider what other challenge tasks for AI could serve a role in CAPTCHAs. The Winograd Schema Challenge (WSC), a certain form of hard pronoun resolution tasks, was proposed by Levesque as such a challenge task to promote research in AI. Based on current reports in the literature, the WSC remains a challenging task for bots, and is, therefore, a candidate to serve as a form of CAPTCHA. In this work we investigate whether this a priori appropriateness of the WSC as a form of CAPTCHA can be justied in terms of its acceptability by the human users in relation to existing CAPTCHA tasks. Our empirical study involved a total of 329 students, aged between 11 and 15, and showed that the WSC is generally faster and easier to solve than, and equally entertaining with, the most typical existing CAPTCHA tasks. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development. ©The authors

The Winograd Schema Challenge (WSC) | the task of resolving pronouns in certain sentences where shallow parsing techniques seem not to be directly applicable | has been proposed as an alternative to the Turing Test. According to Levesque, having access to a large corpus of text would likely not help much in the WSC. Among a number of attempts to tackle this challenge, one particular approach has demonstrated the plausibility of using commonsense knowledge automatically acquired from raw text in English Wikipedia. Here, we present the results of a large-scale experiment that shows how the performance of that particular automated approach varies with the availability of training material. We compare the results of this experiment with two studies: one from the literature that investigates how adult native speakers tackle the WSC, and one that we design and undertake to investigate how teenager non-native speakers tackle the WSC. We nd that the performance of the automated approach correlates positively with the performance of humans, suggesting that the performance of the particular automated approach could be used as a metric of hardness for WSC instances. ; This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development. ©The authors

In this work, we present Web-STAR, an online platform for story understanding built on top of the STAR (STory comprehension through ARgumentation) reasoning engine. This platform includes a web-based IDE, integration with the STAR system and a web service infrastructure to support integration with other systems that rely on story understanding functionality to complete their tasks. The platform also delivers a number of "social" features like public story sharing with a built-in commenting system, a public repository for sharing stories with the community and collaboration tools that can be used from both project team members for development and educators for teaching. Moreover, we discuss the ongoing work on adding new features and functionality to this platform. ; This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development. This article has been published in a revised form in TPLP DOI:10.1017/S1471068418000443. This version is published under a Creative Commons CC-BY-NC-ND. No commercial re-distribution or re-use allowed. Derivative works cannot be distributed. © Cambridge University Press 2018

Despite significant progress in the development of neuralsymbolic frameworks, the question of how to integrate a neural and a symbolic system in a compositional manner remains open. Our work seeks to fill this gap by treating these two systems as black boxes to be integrated as modules into a single architecture, without making assumptions on their internal structure and semantics. Instead, we expect only that each module exposes certain methods for accessing the functions that the module implements: the symbolic module exposes a deduction method for computing the function's output on a given input, and an abduction method for computing the function's inputs for a given output; the neural module exposes a deduction method for computing the function's output on a given input, and an induction method for updating the function given input-output training instances. We are, then, able to show that a symbolic module—with any choice for syntax and semantics, as long as the deduction and abduction methods are exposed — can be cleanly integrated with a neural module, and facilitate the latter's efficient training, achieving empirical performance that exceeds that of previous work. ; This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Republic of Cyprus through the Deputy Ministry of Research, Innovation and Digital Policy.

The right to contest a decision with consequences on individuals or the society is a well-established democratic right. Despite this right also being explicitly included in GDPR in reference to automated decision-making, its study seems to have received much less attention in the AI literature compared, for example, to the right for explanation. This paper investigates the type of assurances that are needed in the contesting process when algorithmic black boxes are involved, opening new questions about the interplay of contestability and explainability. We argue that specialised complementary methodologies to evaluate automated decision-making in the case of a particular decision being contested need to be developed. Further, we propose a combination of well-established software engineering and rule-based approaches as a possible socio-technical solution to the issue of contestability, one of the new democratic challenges posed by the automation of decision making. ; This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Republic of Cyprus through the Deputy Ministry of Research, Innovation and Digital Policy.