Filters








2,514 Hits in 5.5 sec

Generating Dialogues for Virtual Agents Using Nested Textual Coherence Relations [chapter]

Hugo Hernault, Paul Piwek, Helmut Prendinger, Mitsuru Ishizuka
Lecture Notes in Computer Science  
In this paper, we focus on the monologue-to-dialogue transformation, and describe how it uses textual coherence relations to map text segments to query-answer pairs between an expert and a layman agent  ...  Our system enables automatic transformation of monological text into a dialogue. The dialogue is then "acted out" by virtual agents, using synthetic speech and gestures.  ...  This paper presents a significant extension of previously published work [4] in that it introduces a method for generating dialogues from not just flat but also nested coherence relations in text.  ... 
doi:10.1007/978-3-540-85483-8_14 fatcat:hqljpyhz2nbvtfep4vz73k4woa

EMISSOR: A platform for capturing multimodal interactions as Episodic Memories and Interpretations with Situated Scenario-based Ontological References [article]

Selene Báez Santamaría, Thomas Baier, Taewoon Kim, Lea Krause, Jaap Kruijt, Piek Vossen
2021 arXiv   pre-print
EMISSOR can record and annotate experiments in virtual and real-world, combine data, evaluate system behavior and their performance for preset goals but also model the accumulation of knowledge and interpretations  ...  Annotations are eventually mapped to explicit identities and relations in the eKG.  ...  Model causal coherent relations between subsets of segments across modalities 6. Model physical and virtual real-world contexts 7.  ... 
arXiv:2105.08388v1 fatcat:jarhbdfwr5gfdavu2wnndwecda

Programming the Vicious Circle: Austen, Deleuze and Viral Repetition

Mark Horvath, Adam Lovasz
2017 Rhizomes: Cultural Studies in Emerging Knowledge  
In the example of the "Austen-virus," textualities return, reappropriated by malware and other malignant agents.  ...  Agents of multiplicity, such as glitches, bugs and viruses, breed new layers of meaninglessness, spreading chaos throughout networks, blending various strands of code, injecting ruination into coherence  ...  Interobjective dialogue operates on the level of textuality in the manner of a generative imperative.  ... 
doi:10.20415/rhiz/033.e02 fatcat:o4jmo4bavjb4lfucv2jev4b764

Improving Task-Oriented Dialogue Systems In Production with Conversation Logs

Alon Jacovi, Ori Bar El, Ofer Lavi, David Boaz, David Amid, Inbal Ronen, Ateret Anaby-Tavor
2020 Knowledge Discovery and Data Mining  
the poor performance of neural architectures for the task-oriented use-case.  ...  Although current popular taskoriented systems are implemented as rule-based execution graphs, the available solutions for improvement incorporate neural network modules, either fully or partially, despite  ...  Unfortunately, as explained in Section 2, there is currently no method available for making use of this supervision to improve a non-neural dialogue system (the prevailing type of virtual agents in task-oriented  ... 
dblp:conf/kdd/JacoviELBARA20 fatcat:m2l3qlhxnjernnbjoduxqaanmy

Dialogue patterns—A visual language for dynamic dialogue

J. Siegel, D. Szafron
2009 Journal of Visual Languages and Computing  
We present "generative dialogue patterns" as a new visual language for designing dynamic dialogs and generating the program code that is necessary to select the appropriate remarks during the dialogue.  ...  We use a case study from the computer games domain to evaluate the effectiveness of generative dialogue patterns.  ...  We would like to thank the members of the ScriptEase team who provided help and guidance during this research and whose broad shoulders provided the research and development that enabled the dialogue pattern  ... 
doi:10.1016/j.jvlc.2009.02.001 fatcat:2vfmdntiircjvds4agcy2i5rfq

Towards Explainable Social Agent Authoring tools: A case study on FAtiMA-Toolkit [article]

Manuel Guimarães, Joana Campos, Pedro A. Santos, João Dias, Rui Prada
2022 arXiv   pre-print
One of the key findings is the fact that FAtiMA-Toolkit's conceptual model is, in general, understandable, however the emotional-based concepts were not as easily understood and used by the authors.  ...  In this paper we introduce the concept of Explainable Social Agent Authoring Tools with the goal of analysing if authoring tools for social agents are understandable and interpretable.  ...  Acknowledgements This study received Portuguese national funds from FCT -Foundation for Science and Technology through project: UIDB/50021/2020 and UIDB/04326/2020 and SLICE PTDC/CCI-COM/30787/2017.  ... 
arXiv:2206.03360v1 fatcat:n4awqf22fbgjrj3xbf4yqsoxrq

From Information Technologies to Knowledge Technologies?

Jean-Philippe Auzelle, Frédérique Mayer, Pascal Lhoste
2006 IFAC Proceedings Volumes  
The resulting model is used to analyse and to discuss the deficiencies of the current technologies as well as to outline some ways of evolutions for better collaborative knowledge exchanges.  ...  In spite of the large variety of technological means available today to obtain and share knowledge needed by the progress of our Society, the relation between the knowledge produced and the knowledge required  ...  This environment would propose a dialogue with a "virtual man" rather than a screen.  ... 
doi:10.3182/20060522-3-fr-2904.00046 fatcat:57ldxw2svzespevuobklngq5ga

Scientometrics of Deception, Counter-deception, and Deception Detection in Cyber-space

Frank J. Stech, Kristin E. Heckman, Phil Hilliard, Janice Redington Ballo
2011 PsychNology Journal  
into the classic components of denial and deception tactics; there is no conventional terminology to describe the phenomenon of deception in cyber-space; classic deception domain terminology is rarely used  ...  key generation system for agent data protection Ontology-based multi-agent model of an information security system Opponent modeling in poker Optimal Allocation of Resources for Defense of Simple Series  ...  deceptive behavioral cues extracted from video virtual reality training Speech analysis using modulation-based features for detecting deception Using linguistic cues for the automatic recognition of personality  ... 
dblp:journals/psychnology/StechHHB11 fatcat:xxmy5xgr5jfnlpm5uiwpglmrvm

Towards XMAS: eXplainability through Multi-Agent Systems

Giovanni Ciatto, Roberta Calegari, Andrea Omicini, Davide Calvaresi
2019 International Conference of the Italian Association for Artificial Intelligence  
and explainable IS using MAS.  ...  Moreover, Multi-Agent Systems (MAS) achievements and advancements are most often ignored, even when they could bring about key features like explainability and trustworthiness.  ...  For instance, virtual assistants such as Alexa, Cortana, Siri, or Google Home [19] exploit ML to improve a seamless vocal interaction and refined recommendation systems; Nest, the smart thermometer from  ... 
dblp:conf/aiia/CiattoCOC19 fatcat:r6pfsk53avcnjbfv5orwgyjwpa

Naming Trouble in Online Internationalized Education

Catherine Doherty
2009 Pedagogies: An International Journal  
These events are related to the larger problematic of theorising the context of culture in times of globalisation and increasingly entangled educational routes, with implications for the enterprise of  ...  The analysis uses sociolinguistic concepts to analyse selected slices of the online texts and participants' interview accounts.  ...  SFL relates any text to its context of situation, that is, the immediate matter and relations at hand in the textual moment.  ... 
doi:10.1080/15544800903184376 fatcat:b6o56wyuvramto2aub7ui6bm2m

A formal semantics for situated conversation

Julie Hunter, Nicholas Asher, Alex Lascarides
2018 Semantics and Pragmatics  
Table, we infer an event for which Anne is the agent.  ...  each complex discourse unit (CDU) to its sub-units; , a labelling function from elements of E 1 to discourse relation types; and Last, a label for the last unit in V relative to textual order.  ...  Let us now return to our original motivating example Scratches, which involves two dialogue moves, (1) and (2); a head nod; and some scratches s on a wall.  ... 
doi:10.3765/sp.11.10 fatcat:s4pn3ach6zavtafna2axvhcghm

Speech and language processing for next-millennium communications services

R.V. Cox, C.A. Kamm, L.R. Rabiner, J. Schroeter, J.G. Wilpon
2000 Proceedings of the IEEE  
Speech technologies have progressed to the point where they are now viable for a broad range of communications services, including compression of speech for use over wired and wireless networks; speech  ...  synthesis, recognition, and understanding for dialogue access to information, people, and messaging; and speaker verification for secure access to information and services.  ...  Understanding how to use multiple modalities effectively, both for input and output, will be key to providing coherent and robust interactive services on next-generation access devices. V.  ... 
doi:10.1109/5.880086 fatcat:pzd6bawvirfo7c64t4zou2h4hy

Dr 4.2: Multimodal Interaction With Basic Adaptivity And Personalization

Bernd Kiefer, Hans-Ulrich Krieger, Ivana Kruijff-Korbayova, Stefania Racioppa, Franziska Burger, Magdalena Kaiser
2017 Zenodo  
The rst concerns the relation of the child's disclosure depending on self-disclosure of the robotic agent, while the seconds develops strategies how to react to the child's behaviour patterns in using  ...  On the natural language generation side, we implemented basic adaptivity and personalisation, using the data contained in the underlying knowledge source to adapt the conversational style, as well as the  ...  I have profited from discussions with my colleagues Miroslav Janíček, Bernd Kiefer, and Stefan Schulz and would like to thank the ICAART reviewers for their detailed and useful suggestionsthank you guys  ... 
doi:10.5281/zenodo.344181 fatcat:akohq4it55gqldsxtgy2u6qehe

my monstituces composer: Looking for the Pre-Emergent Social Consciousness of AI in Small Data Literary Synthesis

Nathan Allen Jones
2020 Media-N, Journal of the New Media Circus  
more and more human-like textual impersonations.  ...  In one attempt to answer such a question, I make an AI produce faulty, glitchy texts, using a deliberately small corpus, in which the notion of a single-author-trained AI is broken down and confused.  ...  Because probabilistic AI can only extrapolate in relation to a set corpus, it, like a mad professor, becomes less coherently related to its own tradition the more "original" it becomes.  ... 
doi:10.21900/j.median.v16i1.222 fatcat:k5yqtnskvvax7femcex3llskky

One Ontology to Bind Them All: The META-SHARE OWL Ontology for the Interoperability of Linguistic Datasets on the Web [chapter]

John P. McCrae, Penny Labropoulou, Jorge Gracia, Marta Villegas, Víctor Rodríguez-Doncel, Philipp Cimiano
2015 Lecture Notes in Computer Science  
Furthermore, we demonstrate the usefulness of this approach in two public metadata portals for information about language resources.  ...  We show how this model can interface with other more general purpose vocabularies for online datasets and licensing, and apply this model to the CLARIN VLO, a large source of legacy metadata about LRs.  ...  We are very grateful to the members of the W3C Linked Data for Language Technologies (LD4LT) for all the useful feedback received and for allowing this initiative to be developed as an activity of the  ... 
doi:10.1007/978-3-319-25639-9_42 fatcat:3iyokmxqbfeenanpoqwt5yxume
« Previous Showing results 1 — 15 out of 2,514 results