A corpus-based approach to help-desk response generation

Ingrid Zukerman, Yuval Marom

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

    Abstract

    We are developing a corpus-based approach for the prediction of help-desk responses from features in customers ' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic evaluation of the responses generated by our system, as well as a manual one involving human judges. The automatic evaluation involves textual comparisons between generated responses and responses composed by the help-desk operators. The results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.

    Original languageEnglish
    Title of host publicationCIMCA 2006
    Subtitle of host publicationInternational Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies ...
    DOIs
    Publication statusPublished - 1 Dec 2007
    EventCIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies and International Commerce - Sydney, NSW, Australia
    Duration: 28 Nov 20061 Dec 2006

    Conference

    ConferenceCIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies and International Commerce
    CountryAustralia
    CitySydney, NSW
    Period28/11/061/12/06

    Cite this

    Zukerman, I., & Marom, Y. (2007). A corpus-based approach to help-desk response generation. In CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies ... [4052670] https://doi.org/10.1109/CIMCA.2006.2
    Zukerman, Ingrid ; Marom, Yuval. / A corpus-based approach to help-desk response generation. CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies .... 2007.
    @inproceedings{ac5e5465d45a474ab4c4f6af792542cd,
    title = "A corpus-based approach to help-desk response generation",
    abstract = "We are developing a corpus-based approach for the prediction of help-desk responses from features in customers ' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic evaluation of the responses generated by our system, as well as a manual one involving human judges. The automatic evaluation involves textual comparisons between generated responses and responses composed by the help-desk operators. The results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.",
    author = "Ingrid Zukerman and Yuval Marom",
    year = "2007",
    month = "12",
    day = "1",
    doi = "10.1109/CIMCA.2006.2",
    language = "English",
    isbn = "0769527310",
    booktitle = "CIMCA 2006",

    }

    Zukerman, I & Marom, Y 2007, A corpus-based approach to help-desk response generation. in CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies ...., 4052670, CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies and International Commerce, Sydney, NSW, Australia, 28/11/06. https://doi.org/10.1109/CIMCA.2006.2

    A corpus-based approach to help-desk response generation. / Zukerman, Ingrid; Marom, Yuval.

    CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies .... 2007. 4052670.

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

    TY - GEN

    T1 - A corpus-based approach to help-desk response generation

    AU - Zukerman, Ingrid

    AU - Marom, Yuval

    PY - 2007/12/1

    Y1 - 2007/12/1

    N2 - We are developing a corpus-based approach for the prediction of help-desk responses from features in customers ' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic evaluation of the responses generated by our system, as well as a manual one involving human judges. The automatic evaluation involves textual comparisons between generated responses and responses composed by the help-desk operators. The results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.

    AB - We are developing a corpus-based approach for the prediction of help-desk responses from features in customers ' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic evaluation of the responses generated by our system, as well as a manual one involving human judges. The automatic evaluation involves textual comparisons between generated responses and responses composed by the help-desk operators. The results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.

    UR - http://www.scopus.com/inward/record.url?scp=38849169974&partnerID=8YFLogxK

    U2 - 10.1109/CIMCA.2006.2

    DO - 10.1109/CIMCA.2006.2

    M3 - Conference Paper

    SN - 0769527310

    SN - 9780769527314

    BT - CIMCA 2006

    ER -

    Zukerman I, Marom Y. A corpus-based approach to help-desk response generation. In CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies .... 2007. 4052670 https://doi.org/10.1109/CIMCA.2006.2