Alle Publikationen
- <<
- <
- 1
2019
-
(2019): Learning to Have an Ear for Face Super-Resolution. Online verfügbar unter http://arxiv.org/pdf/1909.12780v1
Abstract: We propose a novel method to perform extreme (16x) face super-resolution by exploiting audio. Super-resolution is the task of recovering a high-resolution image from a low-resolution one. When the resolution of the input image is too low (e.g., 8x8 pixels), the loss of information is so dire that the details of the original identity have been lost. However, when the low-resolution image is extracted from a video, the audio track is also available. Because the audio carries information about the face identity, we propose to exploit it in the face reconstruction process. Towards this goal, we propose a model and a training procedure to extract information about the identity of a person from her audio track and to combine it with the information extracted from the low-resolution input image, which relates more to pose and colors of the face. We demonstrate that the combination of these two inputs yields high-resolution images that better capture the correct identity of the face. In particular, we show that audio can assist in recovering attributes such as the gender and the identity, and thus improve the correctness of the image reconstruction process. Our procedure does not make use of human annotation and thus can be easily trained with existing video datasets. Moreover, we show that our model allows one to mix low-resolution images and audio from different videos and to generate realistic faces with semantically meaningful combinations.
2018
-
(2018): Towards a framework for computational persuasion with applications in behaviour change1. In: Argument & Computation 9 (1), S. 15-40. DOI: 10.3233/AAC-170032
DOI: https://doi.org/10.3233/AAC-170032 Abstract: Persuasion is an activity that involves one party trying to induce another party to believe something or to do something. It is an important and multifaceted human facility. Obviously, sales and marketing is heavily dependent on persuasion. But many other activities involve persuasion such as a doctor persuading a patient to drink less alcohol, a road safety expert persuading drivers to not text while driving, or an online safety expert persuading users of social media sites to not reveal too much personal information online. As computing becomes involved in every sphere of life, so too is persuasion a target for applying computer-based solutions. An automated persuasion system (APS) is a system that can engage in a dialogue with a user (the persuadee) in order to persuade the persuadee to do (or not do) some action or to believe (or not believe) something. To do this, an APS aims to use convincing arguments in order to persuade the persuadee. Computational persuasion is the study of formal models of dialogues involving arguments and counterarguments, of user models, and strategies, for APSs. A promising application area for computational persuasion is in behaviour change. Within healthcare organizations, government agencies, and non-governmental agencies, there is much interest in changing behaviour of particular groups of people away from actions that are harmful to themselves and/or to others around them.
Keywords: Argumentation, argumentation strategies, Argumentationsstrategie, Argumentationstheorie, automated persuasion system (APS), Automated Persuasion Systems (APS), computational models of argument, Computational persuasion, Computerbasierte Persuasion, dialogical argumentation, doppelter Treffer, Eliminierung von Fehlverhalten, Fehlverhalten, frame semantics, Gesellschaftsprofit, Gruppenverhalten / Joint Action, Intellektualtechnik, Kognitionstheorie, Kognitionswissenschaft/Social Sciences/Humanities, Mensch-Technik-Relationen (MTR), Observablen/Kriterien für sozial angemessenes Verhalten und dessen Bewertung, Persuasion, persuasion dialogues, persuasive arguments, Politik, probabilistic argumentation, Realtechnik, Soziale Angemessenheit, Sozialer Raum / Kultureller Kontext, Sprachroboter, Sprachverarbeitung, Technik, Überreden, Überzeugung, Umgangsformen, Verführung -
(2018): The knowledge level in cognitive architectures. Current limitations and possible developments. In: COGNITIVE SYSTEMS RESEARCH 48, S. 39-55. DOI: 10.1016/j.cogsys.2017.05.001
Abstract: In this paper we identify and characterize an analysis of two problematic aspects affecting the representational level of cognitive architectures (CAs), namely: the limited size and the homogeneous typology of the encoded and processed knowledge. We argue that such aspects may constitute not only a technological problem that, in our opinion, should be addressed in order to build artificial agents able to exhibit intelligent behaviors in general scenarios, but also an epistemological one, since they limit the plausibility of the comparison of the CAs' knowledge representation and processing mechanisms with those executed by humans in their everyday activities. In the final part of the paper further directions of research will be explored, trying to address current limitations and future challenges. (C) 2017 Elsevier B.V. All rights reserved.
Keywords: Computerwissenschaft, Disziplin, Favoriten, formale Sprache, Formalisierung, Intellektualtechnik, Kogn. Architektur, Kognitionswissenschaft/Social Sciences/Humanities, kognitive Architekturen, Künstliche Intelligenz, Mensch-Technik-Relationen (MTR), natürliche Sprache, Ontologie, Philosophie, Realtechnik, Sprachverarbeitung, Technik, Technikphilosophie, Überblick, Weltwissen -
(2018): Argumentation mining. How can a machine acquire common sense and world knowledge?. In: Argument & Computation 9 (1), S. 1-14. DOI: 10.3233/AAC-170025Keywords: Allgemeiner Sinn, Ambiguität, Argumentation, argumentation mining, Argumentationssuche, Argumentationstheorie, argumentative text processing, Common Sense, Deep Learning, fortgeschrittene interaktive Geräte, frame semantics, Kognitionswissenschaft/Social Sciences/Humanities, Lebenswissen, Linguistik, Mensch-Technik-Relationen (MTR), Natural language understanding, Neural Networks, Realtechnik, representation learning, Sprachverarbeitung, Sprachverstehen, Technik, unsupervised, Voraussetzungen für sozial angemessenes Verhalten, Weltwissen, world knowledge
2017
-
(2017): Structured learning for spoken language understanding in human-robot interaction. In: INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH 36 (5-7), S. 660-683
Abstract: Robots are slowly becoming a part of everyday life, being marketed for commercial applications such as telepresence, cleaning or entertainment. Thus, the ability to interact via natural language with non-expert users is becoming a key requirement. Even if user utterances can be efficiently recognized and transcribed by automatic speech recognition systems, several issues arise in translating them into suitable robotic actions and most of the existing solutions are strictly related to a specific scenario. In this paper, we present an approach to the design of natural language interfaces for human robot interaction, to translate spoken commands into computational structures that enable the robot to execute the intended request. The proposed solution is achieved by combining a general theory of language semantics, i.e. frame semantics, with state-of-the-art methods for robust spoken language understanding, based on structured learning algorithms. The adopted data driven paradigm allows the development of a fully functional natural language processing chain, that can be initialized by re-using available linguistic tools and resources. In addition, it can be also specialized by providing small sets of examples representative of a target newer domain. A systematic benchmarking resource, in terms of a rich and multi-layered spoken corpus has also been created and it has been used to evaluate the natural language processing chain. Our results show that our processing chain, trained with generic resources, provides a solid baseline for command understanding in a service robot domain. Moreover, when domain-dependent resources are provided to the system, the accuracy of the achieved interpretation always improves.
Keywords: Algorithmen, doppelter Treffer, frame semantics, Frame-Semantik, Interaktion, Korpus, Mensch-Maschine-Kommunikation, Mensch-Technik-Interaktion, Mensch-Technik-Relationen (MTR), narürliche Sprache, natural language interface, Observablen/Kriterien für sozial angemessenes Verhalten und dessen Bewertung, Realtechnik, Robotik, Serviceroboter, Soziale Angemessenheit, Soziale Robotik, speech processing, Sprache, Sprachgebrauch, Sprachverarbeitung, Sprachverstehen, Status / biologische Marker, structured learning algorithm, Technik -
(2017) : Strategies and mechanisms to enable dialogue agents to respond appropriately to indirect speech acts In: IEEE Ro-Man: Human-robot collaboration and human assistance for an improved quality of life: IEEE RO-MAN 2017 : 26th IEEE International Symposium on Robot and Human Ineractive Communication : August 28-September 1, 2017, Lisbon, Portugal: Piscataway, NJ: IEEE, S. 323-328
Abstract: Humans often use indirect speech acts (ISAs) when issuing directives. Much of the work in handling ISAs in computational dialogue architectures has focused on correctly identifying and handling the underlying non-literal meaning. There has been less attention devoted to how linguistic responses to ISAs might differ from those given to literal directives and how to enable different response forms in these computational dialogue systems. In this paper, we present ongoing work toward developing dialogue mechanisms within a cognitive, robotic architecture that enables a richer set of response strategies to non-literal directives.
Keywords: Antworten im Rahmen einer Konversation, Computerwissenschaft, indirect speech acts, Indirektheit, Informations- & Kommunikationstechnik, Interaktionspartner, Konversationsanalyse, Korrespondenz, Künstliche Intelligenz, Linguistik, Mensch oder Maschine, Mensch-Technik-Relationen (MTR), nicht wörtlich, non-literal meaning, Realtechnik, Semantik, Soziale Robotik, Sprachgebrauch, Sprachroboter, Sprachverarbeitung, Sprechakt, Technik, Unterschiedliche Antworten je nach Direktheit/Indirektheit des vorherigen Sprechaktes -
(2017): Making sense of words. A robotic model for language abstraction. In: Autonomous Robots 41 (2), S. 367-383. DOI: 10.1007/s10514-016-9587-8
Abstract: Building robots capable of acting independently in unstructured environments is still a challenging task for roboticists. The capability to comprehend and produce language in a 'human-like' manner represents a powerful tool for the autonomous interaction of robots with human beings, for better understanding situations and exchanging information during the execution of tasks that require cooperation. In this work, we present a robotic model for grounding abstract action words (i.e. USE, MAKE) through the hierarchical organization of terms directly linked to perceptual and motor skills of a humanoid robot. Experimental results have shown that the robot, in response to linguistic commands, is capable of performing the appropriate behaviors on objects. Results obtained in case of inconsistency between the perceptual and linguistic inputs have shown that the robot executes the actions elicited by the seen object.
2015
-
(2015): Disrupting morphosyntactic and lexical semantic processing has opposite effects on the sample entropy of neural signals. In: BRAIN RESEARCH 1604, S. 1-14
Abstract: Converging evidence in neuroscience suggests that syntax and semantics are dissociable in brain space and time. However, it is possible that partly disjoint cortical networks, operating in successive time frames, still perform similar types of neural computations. To test the alternative hypothesis, we collected EEG data while participants read sentences containing lexical semantic or morphosyntactic anomalies, resulting in N400 and P600 effects, respectively. Next, we reconstructed phase space trajectories from EEG time series, and we measured the complexity of the resulting dynamical orbits using sample entropy an index of the rate at which the system generates or loses information over time. Disrupting morphosyntactic or lexical semantic processing had opposite effects on sample entropy: it increased in the N400 window for semantic anomalies, and it decreased in the P600 window for morphosyntactic anomalies. These findings point to a fundamental divergence in the neural computations supporting meaning and grammar in language. (C) 2015 Elsevier B.V. All rights reserved.
Keywords: Bedeutung, Bedeutung und Grammatik, Bedeutungszusammenhang, frame semantics, Grammar, Grammatiktheorie, Intellektualtechnik, Kogn. Architektur, Kognitionswissenschaft/Social Sciences/Humanities, Kognitive Skills/Social Cognition, lexikalische Semantik, Meaning, Mensch-Technik-Relationen (MTR), Neurowissenschaften, Sprache, Sprachverarbeitung, Sprachverstehen, Technik, Voraussetzungen für sozial angemessenes Verhalten 2013
-
(2013): The Effect of Priming Pictures and Videos on a Question–Answer Dialog Scenario in a Virtual Environment. In: Presence: Teleoperators and Virtual Environments 22 (2), S. 91-109. DOI: 10.1162/PRES_a_00143
Abstract: Having a free-speech conversation with avatars in a virtual environment can be desirable in virtual reality applications, such as virtual therapy and serious games. However, recognizing and processing free speech seems too ambitious to realize with the current technology. As an alternative, pre-scripted conversations with keyword detection can handle a number of goal-oriented situations, as well as some scenarios in which the conversation content is of secondary importance. This is, for example, the case in virtual exposure therapy for the treatment of people with social phobia, where conversation is for exposure and anxiety arousal only. A drawback of pre-scripted dialog is the limited scope of the user's answers. The system cannot handle a user's response that does not match the pre-defined content, other than by providing a default reply. A new method, which uses priming material to restrict the possibility of the user's response, is proposed in this paper to solve this problem. Two studies were conducted to investigate whether people can be guided to mention specific keywords with video and/or picture primings. Study 1 was a two-by-two experiment in which participants (n = 20) were asked to answer a number of open questions. Prior to the session, participants watched priming videos or unrelated videos. During the session, they could see priming pictures or unrelated pictures on a whiteboard behind the person who asked the questions. The results showed that participants tended to mention more keywords both with priming videos and pictures. Study 2 shared the same experimental setting but was carried out in virtual reality instead of in the real world. Participants (n = 20) were asked to answer questions of an avatar when they were exposed to priming material, before and/or during the conversation session. The same results were found: the surrounding media content had a guidance effect. Furthermore, when priming pictures appeared in the environment, people sometimes forgot to mention the content they typically would mention.
Keywords: ACROPHOBIA, Augmented & Virtual Reality, Beeinflussung sozial angemessenen Verhaltens, BEHAVIOR, DISORDERS therapy, FEAR, IN-VIVO, Mensch-Technik-Relationen (MTR), METAANALYSIS, Psychologie, PUBLIC-SPEAKING ANXIETY, REALITY EXPOSURE THERAPY, Realtechnik, SOCIAL PHOBIA, Sonder-Intention beim Sprechen/Konversation, SPIDER PHOBIA, Sprachverarbeitung, Technik, technology in therapy, Therapeutische Zwecke, Triggern von angstauslösenden Begriffen, Video/picture priming
- <<
- <
- 1