Optimizing method for structuring inferentially linked discourse

Ingrid Zukerman, Richard McConachy

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

    1 Citation (Scopus)

    Abstract

    In recent times, there has been an increase in the number of Natural Language Generation systems that take into consideration a user's inferences. The statements generated by these systems are typically connected by inferential links, which are opportunistic in nature. In this paper, we describe a discourse structuring mechanism which organizes inferentially linked statements as well as statements connected by certain prescriptive links. Our mechanism first extracts relations and constraints from the output of a discourse planner. It then uses this information to build a directed graph whose nodes are rhetorical devices, and whose links are the relations between these devices. The mechanism then applies a search procedure to optimize the traversal through the graph. This process generates an ordered set of linear discourse sequences, where the elements of each sequence are maximally connected. Our mechanism has been implemented as the discourse organization component of a system called WISHFUL which generates concept explanations.

    Original languageEnglish
    Title of host publicationProceedings of the National Conference on Artificial Intelligence
    PublisherPubl by AAAI
    Pages202-207
    Number of pages6
    ISBN (Print)0262510715
    Publication statusPublished - 1 Dec 1993
    EventProceedings of the 11th National Conference on Artificial Intelligence - Washington, United States of America
    Duration: 11 Jul 199315 Jul 1993

    Conference

    ConferenceProceedings of the 11th National Conference on Artificial Intelligence
    CountryUnited States of America
    CityWashington
    Period11/07/9315/07/93

    Cite this

    Zukerman, I., & McConachy, R. (1993). Optimizing method for structuring inferentially linked discourse. In Proceedings of the National Conference on Artificial Intelligence (pp. 202-207). Publ by AAAI.
    Zukerman, Ingrid ; McConachy, Richard. / Optimizing method for structuring inferentially linked discourse. Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI, 1993. pp. 202-207
    @inproceedings{58fd192a7eb44da68a30ee1c36baa070,
    title = "Optimizing method for structuring inferentially linked discourse",
    abstract = "In recent times, there has been an increase in the number of Natural Language Generation systems that take into consideration a user's inferences. The statements generated by these systems are typically connected by inferential links, which are opportunistic in nature. In this paper, we describe a discourse structuring mechanism which organizes inferentially linked statements as well as statements connected by certain prescriptive links. Our mechanism first extracts relations and constraints from the output of a discourse planner. It then uses this information to build a directed graph whose nodes are rhetorical devices, and whose links are the relations between these devices. The mechanism then applies a search procedure to optimize the traversal through the graph. This process generates an ordered set of linear discourse sequences, where the elements of each sequence are maximally connected. Our mechanism has been implemented as the discourse organization component of a system called WISHFUL which generates concept explanations.",
    author = "Ingrid Zukerman and Richard McConachy",
    year = "1993",
    month = "12",
    day = "1",
    language = "English",
    isbn = "0262510715",
    pages = "202--207",
    booktitle = "Proceedings of the National Conference on Artificial Intelligence",
    publisher = "Publ by AAAI",

    }

    Zukerman, I & McConachy, R 1993, Optimizing method for structuring inferentially linked discourse. in Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI, pp. 202-207, Proceedings of the 11th National Conference on Artificial Intelligence, Washington, United States of America, 11/07/93.

    Optimizing method for structuring inferentially linked discourse. / Zukerman, Ingrid; McConachy, Richard.

    Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI, 1993. p. 202-207.

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

    TY - GEN

    T1 - Optimizing method for structuring inferentially linked discourse

    AU - Zukerman, Ingrid

    AU - McConachy, Richard

    PY - 1993/12/1

    Y1 - 1993/12/1

    N2 - In recent times, there has been an increase in the number of Natural Language Generation systems that take into consideration a user's inferences. The statements generated by these systems are typically connected by inferential links, which are opportunistic in nature. In this paper, we describe a discourse structuring mechanism which organizes inferentially linked statements as well as statements connected by certain prescriptive links. Our mechanism first extracts relations and constraints from the output of a discourse planner. It then uses this information to build a directed graph whose nodes are rhetorical devices, and whose links are the relations between these devices. The mechanism then applies a search procedure to optimize the traversal through the graph. This process generates an ordered set of linear discourse sequences, where the elements of each sequence are maximally connected. Our mechanism has been implemented as the discourse organization component of a system called WISHFUL which generates concept explanations.

    AB - In recent times, there has been an increase in the number of Natural Language Generation systems that take into consideration a user's inferences. The statements generated by these systems are typically connected by inferential links, which are opportunistic in nature. In this paper, we describe a discourse structuring mechanism which organizes inferentially linked statements as well as statements connected by certain prescriptive links. Our mechanism first extracts relations and constraints from the output of a discourse planner. It then uses this information to build a directed graph whose nodes are rhetorical devices, and whose links are the relations between these devices. The mechanism then applies a search procedure to optimize the traversal through the graph. This process generates an ordered set of linear discourse sequences, where the elements of each sequence are maximally connected. Our mechanism has been implemented as the discourse organization component of a system called WISHFUL which generates concept explanations.

    UR - http://www.scopus.com/inward/record.url?scp=0027706954&partnerID=8YFLogxK

    M3 - Conference Paper

    SN - 0262510715

    SP - 202

    EP - 207

    BT - Proceedings of the National Conference on Artificial Intelligence

    PB - Publ by AAAI

    ER -

    Zukerman I, McConachy R. Optimizing method for structuring inferentially linked discourse. In Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI. 1993. p. 202-207