Publications

This is the publication list related to the AgentSlang platform. In order to cite properly our work, please use the latest paper available.

2014

  • Ovidiu Șerban. Syn!bad: a synonym-based regular expression extension for knowledge extraction tasks. Studia universitatis babes-bolyai, series informatica, LIX(1):5-15, June 2014.
    [BibTeX] [Abstract] [Download PDF]

    This paper focuses on presenting Syn!bad, a synonym-based regular expression language which can be used for basic Knowledge Extraction tasks, such as the Natural Language Understanding components for Dialogue Management. The language o ers a simple syntax for complex matching processes, which brings a new solution for the input variability problem, often encountered when dealing with natural language. The language provides various special tokens to match synonym-based expressions free context variables and generic Part of Speech tokens.

    @article{serban2014synnbad,
    title={Syn!bad: A Synonym-Based Regular Expression Extension For Knowledge Extraction Tasks},
    author={Șerban, Ovidiu},
    journal = "Studia Universitatis Babes-Bolyai, Series Informatica",
    volume = "LIX",
    number = "1",
    pages = "5--15",
    year = "2014",
    month = "June",
    abstract={This paper focuses on presenting Syn!bad, a synonym-based
    regular expression language which can be used for basic Knowledge Extraction tasks, such as the Natural Language Understanding components for Dialogue Management. The language oers a simple syntax for complex matching processes, which brings a new solution for the input variability problem, often encountered when dealing with natural language. The language provides various special tokens to match synonym-based expressions free context variables and generic Part of Speech tokens.},
    url={http://www.cs.ubbcluj.ro/~studia-i/2014-1/01-Serban.pdf}
    }

  • William Boisseleau, Ovidiu Șerban, and Alexandre Pauchet. Building a narrative conversational agent using a component-based architecture. In Aamas 2014 demo track. AAMAS,, 2014.
    [BibTeX]
    @inproceedings{boisseleau2014agentslang,
    title={Building a Narrative Conversational Agent using a Component-based Architecture},
    author={Boisseleau, William and Șerban, Ovidiu and Pauchet, Alexandre},
    booktitle={AAMAS 2014 DEMO Track},
    year={2014},
    organization={AAMAS},
    abstract={},
    url={}
    }

  • Ovidiu Șerban and Alexandre Pauchet. Agentslang: a new distributed interactive system.current approaches and performance. In Proceedings of the 6th international conference on agents and artificial intelligence (icaart). SciTePress,, 2014.
    [BibTeX] [Abstract]

    This paper proposes a generic platform for developing fast and reliable Distributed Interactive Systems. The modelling is based on a component design approach, with element structure simple and versatile enough to allow the integration of existing algorithms. The AgentSlang platform consists in a series of original components integrated with several existing algorithms, to provide a development environment for Interactive Systems. There are several original parts in our approach. First, the platform is based on a data and component oriented design, which integrates into a unified system the concept of Feedback Management, Dialogue Management and a flexible component architecture. Second, the Syn!bad language, is integrated as a component of AgentSlang. Third, the message exchange speed is superior of any existing platforms, even in the context of providing extra features, such as action execution feedback and data type consistency check.

    @inproceedings{serban2014agentslang,
    title={AgentSlang: a New Distributed Interactive System.Current Approaches and Performance},
    author={Șerban, Ovidiu and Pauchet, Alexandre},
    booktitle={Proceedings of the 6th International Conference on Agents and Artificial Intelligence (ICAART)},
    year={2014},
    organization={SciTePress},
    abstract={This paper proposes a generic platform for developing fast and reliable Distributed Interactive Systems. The modelling is based on a component design approach, with element structure simple and versatile enough to allow the integration of existing algorithms. The AgentSlang platform consists in a series of original components integrated with several existing algorithms, to provide a development environment for Interactive Systems. There are several original parts in our approach. First, the platform is based on a data and component
    oriented design, which integrates into a unified system the concept of Feedback Management, Dialogue Management and a flexible component architecture. Second, the Syn!bad language, is integrated as a component of AgentSlang. Third, the message exchange speed is superior of any existing platforms, even in the context of providing extra features, such as action execution feedback and data type consistency check.},
    url={}
    }

2013

  • Ovidiu Șerban and Alexandre Pauchet. Agentslang: a fast and reliable platform for distributed interactive systems. In Intelligent computer communication and processing (iccp), 2013 ieee international conference on, pages 35-42. IEEE,, 2013.
    [BibTeX] [Abstract] [Download PDF]

    This paper proposes a generic platform for developing fast and reliable Distributed Interactive Systems. The modelling is based on a component design approach, with element structure simple and versatile enough to allow the integration of existing algorithm. Moreover, we propose Syn!bad as a unified knowledge extraction language, focused around the usage of synonyms, useful for dialogue management. The AgentSlang platform consists in a series of original components integrated with several existing algorithms, to provide a development environment for Interactive Systems. There are several original parts in our approach. First, the platform is based on a data and component oriented design, which integrates into a unified system the concept of Feedback Management, Dialogue Management and a flexible component architecture. Second, the Syn!bad language, is integrated as a component of AgentSlang. Third, the message exchange speed is superior of any existing platforms, even in the context of providing extra features, such as action execution feedback and data type consistency check.

    @inproceedings{serban2013agentslang,
    title={AgentSlang: A fast and reliable platform for Distributed Interactive Systems},
    author={Șerban, Ovidiu and Pauchet, Alexandre},
    booktitle={Intelligent Computer Communication and Processing (ICCP), 2013 IEEE International Conference on},
    pages={35--42},
    year={2013},
    organization={IEEE},
    abstract={This paper proposes a generic platform for developing fast and reliable Distributed Interactive Systems. The modelling is based on a component design approach, with element structure simple and versatile enough to allow the integration of existing algorithm. Moreover, we propose Syn!bad as a unified knowledge extraction language, focused around the usage of synonyms, useful for dialogue management. The AgentSlang platform consists in a series of original components integrated with several existing algorithms, to provide a development environment for Interactive Systems. There are several original parts in our approach. First, the platform is based on a data and component oriented design, which integrates into a unified system the concept of Feedback Management, Dialogue Management and a flexible component architecture. Second, the Syn!bad language, is integrated as a component of AgentSlang. Third, the message exchange speed is superior of any existing platforms, even in the context of providing extra features, such as action execution feedback and data type consistency check.},
    url={http://ieeexplore.ieee.org/iel7/6636285/6646058/06646077.pdf?arnumber=6646077}
    }

  • Ovidiu Șerban. Detection and integration of affective feedback into distributed interactive systems. PhD thesis, INSA de Rouen (France) and "Babeș-Bolyai" University (Romania), 2013.
    [BibTeX] [Abstract] [Download PDF]

    Human-Computer Interaction migrates from the classic perspective to a more natural environment, where humans are able to use natural language to exchange knowledge with a computer. In order to fully "understand" the human’s intentions, the computer should be able to detect emotions and reply accordingly. This thesis focuses on several issues regarding the human affects, from various detection techniques to their integration into a Distributed Interactive System. Emotions are a fuzzy concept and their perception across human individuals may vary as well. Therefore, this makes the detection problem very difficult for a computer. From the affect detection perspective, we proposed three different approaches: an emotion detection method based on Self Organizing Maps, a valence classifier based on multi-modal features and Support Vector Machines, and a technique to resolve conflicts into a well known affective dictionary (SentiWordNet). Moreover, from the system integration perspective, two issues are approached: a Wizard of Oz experiment in a children storytelling environment and an architecture for a Distributed Interactive System.

    @phdthesis{serban2013phd,
    title={Detection and Integration of Affective Feedback into Distributed Interactive Systems},
    author={Șerban, Ovidiu},
    school={INSA de Rouen (France) and "Babeș-Bolyai" University (Romania)},
    year={2013},
    abstract={Human-Computer Interaction migrates from the classic perspective to a more natural environment, where humans are able to use natural language to exchange knowledge with a computer. In order to fully "understand" the human's intentions, the computer should be able to detect emotions and reply accordingly. This thesis focuses on several issues regarding the human affects, from various detection techniques to their integration into a Distributed Interactive System.
    Emotions are a fuzzy concept and their perception across human individuals may vary as well. Therefore, this makes the detection problem very difficult for a computer. From the affect detection perspective, we proposed three different approaches: an emotion detection method based on Self Organizing Maps, a valence classifier based on multi-modal features and Support Vector Machines, and a technique to resolve conflicts into a well known affective dictionary (SentiWordNet). Moreover, from the system integration perspective, two issues are approached: a Wizard of Oz experiment in a children storytelling environment and an architecture for a Distributed Interactive System.},
    url={http://ovidiu.roboslang.org/upload/articles/OvidiuSerban-PhDThesis.pdf}
    }

  • William Boisseleau. Intégration de composants à un agent conversationnel animé. Technical Report, INSA de Rouen (France), 2013.
    [BibTeX] [Abstract] [Download PDF]

    Notre société est aujourd’hui de plus en plus dépendante des machines physiques et immatérielles dans de nombreux domaines, tels que l’industrie, la recherche, et même les services. Par extension, l’évolution technologique et humaine est étroitement liée aux algorithmes faisant tourner ces-dites machines, et leur étude approfondie depuis seulement une cinquantaine d’années a permis de grandes avancées. Il ne s’agit pas d’améliorer seulement les composants internes, propres à ces algorithmes, mais également d’implémenter une interaction homme/machine la plus optimale, afin d’en parfaire les résultats. Ainsi, c’est sous le thème des interactions que le stage de spécialité ici rapporté s’est déroulé.

    @techreport{boisseleau2013report,
    title={Intégration de Composants à un Agent Conversationnel Animé},
    author={Boisseleau, William},
    institution={INSA de Rouen (France)},
    year={2013},
    abstract={Notre société est aujourd'hui de plus en plus dépendante des machines physiques et immatérielles dans de nombreux domaines, tels que l'industrie, la recherche, et même les services. Par extension, l'évolution technologique et humaine est étroitement liée aux algorithmes faisant tourner ces-dites machines, et leur étude approfondie depuis seulement une cinquantaine d'années a permis de grandes avancées. Il ne s'agit pas d'améliorer seulement les composants internes, propres à ces algorithmes, mais également d'implémenter une interaction homme/machine la plus optimale, afin d'en parfaire les résultats. Ainsi, c'est sous le thème des interactions que le stage de spécialité ici rapporté s'est déroulé.},
    url={http://ovidiu.roboslang.org/upload/articles/WilliamBoisseleau-TechnicalReport.pdf}
    }

2012

  • Zacharie Ales, Dubuisson G. Duplessis, Ovidiu Șerban, and Alexandre Pauchet. A methodology to design human-like embodied conversational agents based on dialogue analysis. , pages 34-50, 2012.
    [BibTeX] [Abstract] [Download PDF]

    This paper presents a bottom-up methodology to study human-human and human-agent dialogues in order to improve the design of embodied conversational agents (ECAs). The methodology uses a matrix representation of dialogues, constructed by means of a (semi-)automatic annotation process. A multidimensional dialogue pattern extraction and a clustering algorithm are applied to the coding matrices. The extracted patterns model the human behaviours.

    @article{alesmethodology,
    title={A Methodology to Design Human-Like Embodied Conversational Agents based on Dialogue Analysis},
    author={Ales, Zacharie and Duplessis, G Dubuisson and Șerban, Ovidiu and Pauchet, Alexandre},
    booktitle={First International Workshop on Human-Agent Interaction Design and Models (HAIDM)},
    pages={34--50},
    year={2012},
    organization={AAMAS},
    abstract={This paper presents a bottom-up methodology to study human-human and human-agent dialogues in order to improve the design of embodied conversational agents (ECAs). The methodology uses a matrix representation of dialogues, constructed by means of a (semi-)automatic annotation process. A multidimensional dialogue pattern extraction and a clustering algorithm are applied to the coding matrices. The extracted patterns model the human behaviours.},
    url={http://asi.insa-rouen.fr/enseignants/~apauchet/Files/Publications/HAIDM'12.pdf}
    }