A comparison of addressee detection methods for multiparty conversations

Rieks op den Akker, David Traum

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    23 Downloads (Pure)

    Abstract

    Several algorithms have recently been proposed for recognizing addressees in a group conversational setting. These algorithms can rely on a variety of factors including previous conversational roles, gaze and type of dialogue act. Both statistical supervised machine learning algorithms as well as rule based methods have been developed. In this paper, we compare several algorithms developed for several different genres of muliparty dialogue, and propose a new synthesis algorithm that matches the performance of machine learning algorithms while maintaning the transparancy of semantically meaningfull rule-based algorithms.
    Original languageEnglish
    Title of host publicationProceedings of DiaHolmia 2009
    Subtitle of host publication13th Workshop on the Semantics and Pragmatics of Dialogue
    EditorsJens Edlund, Joakim Gustafson, Anna Hjalmarsson, Gabriel Skantze
    Place of PublicationStockholm
    PublisherKTH Royal Institute of Technology
    Pages99-106
    Number of pages8
    Publication statusPublished - 24 Jun 2009
    Event13th Workshop on the Semantics and Pragmatics of Dialogue, SemDial 2009: DiaHolmia - Sockholm, Sweden
    Duration: 24 Jun 200926 Jun 2009
    Conference number: 13

    Workshop

    Workshop13th Workshop on the Semantics and Pragmatics of Dialogue, SemDial 2009
    Abbreviated titleSemDial
    CountrySweden
    CitySockholm
    Period24/06/0926/06/09

    Fingerprint

    Learning algorithms
    Learning systems

    Keywords

    • METIS-275560
    • Machine classification
    • IR-75327
    • EWI-17164
    • EC Grant Agreement nr.: FP6/0033812
    • HMI-MI: MULTIMODAL INTERACTIONS
    • multimodal recognition machine classification
    • Multimodal recognition

    Cite this

    op den Akker, R., & Traum, D. (2009). A comparison of addressee detection methods for multiparty conversations. In J. Edlund, J. Gustafson, A. Hjalmarsson, & G. Skantze (Eds.), Proceedings of DiaHolmia 2009: 13th Workshop on the Semantics and Pragmatics of Dialogue (pp. 99-106). Stockholm: KTH Royal Institute of Technology.
    op den Akker, Rieks ; Traum, David. / A comparison of addressee detection methods for multiparty conversations. Proceedings of DiaHolmia 2009: 13th Workshop on the Semantics and Pragmatics of Dialogue. editor / Jens Edlund ; Joakim Gustafson ; Anna Hjalmarsson ; Gabriel Skantze. Stockholm : KTH Royal Institute of Technology, 2009. pp. 99-106
    @inproceedings{f1a29dea2ee24cd9b96f7ca66d6d2e12,
    title = "A comparison of addressee detection methods for multiparty conversations",
    abstract = "Several algorithms have recently been proposed for recognizing addressees in a group conversational setting. These algorithms can rely on a variety of factors including previous conversational roles, gaze and type of dialogue act. Both statistical supervised machine learning algorithms as well as rule based methods have been developed. In this paper, we compare several algorithms developed for several different genres of muliparty dialogue, and propose a new synthesis algorithm that matches the performance of machine learning algorithms while maintaning the transparancy of semantically meaningfull rule-based algorithms.",
    keywords = "METIS-275560, Machine classification, IR-75327, EWI-17164, EC Grant Agreement nr.: FP6/0033812, HMI-MI: MULTIMODAL INTERACTIONS, multimodal recognition machine classification, Multimodal recognition",
    author = "{op den Akker}, Rieks and David Traum",
    year = "2009",
    month = "6",
    day = "24",
    language = "English",
    pages = "99--106",
    editor = "Jens Edlund and Joakim Gustafson and Anna Hjalmarsson and Gabriel Skantze",
    booktitle = "Proceedings of DiaHolmia 2009",
    publisher = "KTH Royal Institute of Technology",
    address = "Sweden",

    }

    op den Akker, R & Traum, D 2009, A comparison of addressee detection methods for multiparty conversations. in J Edlund, J Gustafson, A Hjalmarsson & G Skantze (eds), Proceedings of DiaHolmia 2009: 13th Workshop on the Semantics and Pragmatics of Dialogue. KTH Royal Institute of Technology, Stockholm, pp. 99-106, 13th Workshop on the Semantics and Pragmatics of Dialogue, SemDial 2009, Sockholm, Sweden, 24/06/09.

    A comparison of addressee detection methods for multiparty conversations. / op den Akker, Rieks; Traum, David.

    Proceedings of DiaHolmia 2009: 13th Workshop on the Semantics and Pragmatics of Dialogue. ed. / Jens Edlund; Joakim Gustafson; Anna Hjalmarsson; Gabriel Skantze. Stockholm : KTH Royal Institute of Technology, 2009. p. 99-106.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - A comparison of addressee detection methods for multiparty conversations

    AU - op den Akker, Rieks

    AU - Traum, David

    PY - 2009/6/24

    Y1 - 2009/6/24

    N2 - Several algorithms have recently been proposed for recognizing addressees in a group conversational setting. These algorithms can rely on a variety of factors including previous conversational roles, gaze and type of dialogue act. Both statistical supervised machine learning algorithms as well as rule based methods have been developed. In this paper, we compare several algorithms developed for several different genres of muliparty dialogue, and propose a new synthesis algorithm that matches the performance of machine learning algorithms while maintaning the transparancy of semantically meaningfull rule-based algorithms.

    AB - Several algorithms have recently been proposed for recognizing addressees in a group conversational setting. These algorithms can rely on a variety of factors including previous conversational roles, gaze and type of dialogue act. Both statistical supervised machine learning algorithms as well as rule based methods have been developed. In this paper, we compare several algorithms developed for several different genres of muliparty dialogue, and propose a new synthesis algorithm that matches the performance of machine learning algorithms while maintaning the transparancy of semantically meaningfull rule-based algorithms.

    KW - METIS-275560

    KW - Machine classification

    KW - IR-75327

    KW - EWI-17164

    KW - EC Grant Agreement nr.: FP6/0033812

    KW - HMI-MI: MULTIMODAL INTERACTIONS

    KW - multimodal recognition machine classification

    KW - Multimodal recognition

    M3 - Conference contribution

    SP - 99

    EP - 106

    BT - Proceedings of DiaHolmia 2009

    A2 - Edlund, Jens

    A2 - Gustafson, Joakim

    A2 - Hjalmarsson, Anna

    A2 - Skantze, Gabriel

    PB - KTH Royal Institute of Technology

    CY - Stockholm

    ER -

    op den Akker R, Traum D. A comparison of addressee detection methods for multiparty conversations. In Edlund J, Gustafson J, Hjalmarsson A, Skantze G, editors, Proceedings of DiaHolmia 2009: 13th Workshop on the Semantics and Pragmatics of Dialogue. Stockholm: KTH Royal Institute of Technology. 2009. p. 99-106