A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations

Jonathon Read, Erik Velldal, Marc Cavazza, Gersende Georg

    Research output: Contribution to conferencePaperResearchpeer-review

    3 Downloads (Pure)

    Abstract

    In this paper we present the Corpus of REcommendation STrength (CREST), a collection of HTML-formatted clinical guidelines annotated with the location of recommendations. Recommendations are labelled with an author-provided indicator of their strength of importance. As data was drawn from many disparate authors, we define a unified scheme of importance labels, and provide a mapping for each guideline. We demonstrate the utility of the corpus and its annotations in some initial measurements investigating the type of language construc- tions associated with strong and weak recommendations, and experiments into promising features for recommendation classification, both with respect to strong and weak labels, and to all labels of the unified scheme. An error analysis indicates that, while there is a strong relationship between lexical choices and strength labels, there can be substantial variance in the choices made by different authors.
    Original languageEnglish
    Publication statusPublished - 23 May 2016
    Event10th Language Resources and Evaluation Conference - Portorož, Slovenia
    Duration: 23 May 201628 May 2016

    Conference

    Conference10th Language Resources and Evaluation Conference
    CountrySlovenia
    CityPortorož
    Period23/05/1628/05/16

    Fingerprint

    error analysis
    recommendation
    experiment
    indicator

    Cite this

    Read, J., Velldal, E., Cavazza, M., & Georg, G. (2016). A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations. Paper presented at 10th Language Resources and Evaluation Conference, Portorož, Slovenia.
    Read, Jonathon ; Velldal, Erik ; Cavazza, Marc ; Georg, Gersende. / A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations. Paper presented at 10th Language Resources and Evaluation Conference, Portorož, Slovenia.
    @conference{0902c08720d14a0aae06c54c0b7325dc,
    title = "A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations",
    abstract = "In this paper we present the Corpus of REcommendation STrength (CREST), a collection of HTML-formatted clinical guidelines annotated with the location of recommendations. Recommendations are labelled with an author-provided indicator of their strength of importance. As data was drawn from many disparate authors, we define a unified scheme of importance labels, and provide a mapping for each guideline. We demonstrate the utility of the corpus and its annotations in some initial measurements investigating the type of language construc- tions associated with strong and weak recommendations, and experiments into promising features for recommendation classification, both with respect to strong and weak labels, and to all labels of the unified scheme. An error analysis indicates that, while there is a strong relationship between lexical choices and strength labels, there can be substantial variance in the choices made by different authors.",
    author = "Jonathon Read and Erik Velldal and Marc Cavazza and Gersende Georg",
    year = "2016",
    month = "5",
    day = "23",
    language = "English",
    note = "10th Language Resources and Evaluation Conference ; Conference date: 23-05-2016 Through 28-05-2016",

    }

    Read, J, Velldal, E, Cavazza, M & Georg, G 2016, 'A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations' Paper presented at 10th Language Resources and Evaluation Conference, Portorož, Slovenia, 23/05/16 - 28/05/16, .

    A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations. / Read, Jonathon; Velldal, Erik; Cavazza, Marc; Georg, Gersende.

    2016. Paper presented at 10th Language Resources and Evaluation Conference, Portorož, Slovenia.

    Research output: Contribution to conferencePaperResearchpeer-review

    TY - CONF

    T1 - A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations

    AU - Read, Jonathon

    AU - Velldal, Erik

    AU - Cavazza, Marc

    AU - Georg, Gersende

    PY - 2016/5/23

    Y1 - 2016/5/23

    N2 - In this paper we present the Corpus of REcommendation STrength (CREST), a collection of HTML-formatted clinical guidelines annotated with the location of recommendations. Recommendations are labelled with an author-provided indicator of their strength of importance. As data was drawn from many disparate authors, we define a unified scheme of importance labels, and provide a mapping for each guideline. We demonstrate the utility of the corpus and its annotations in some initial measurements investigating the type of language construc- tions associated with strong and weak recommendations, and experiments into promising features for recommendation classification, both with respect to strong and weak labels, and to all labels of the unified scheme. An error analysis indicates that, while there is a strong relationship between lexical choices and strength labels, there can be substantial variance in the choices made by different authors.

    AB - In this paper we present the Corpus of REcommendation STrength (CREST), a collection of HTML-formatted clinical guidelines annotated with the location of recommendations. Recommendations are labelled with an author-provided indicator of their strength of importance. As data was drawn from many disparate authors, we define a unified scheme of importance labels, and provide a mapping for each guideline. We demonstrate the utility of the corpus and its annotations in some initial measurements investigating the type of language construc- tions associated with strong and weak recommendations, and experiments into promising features for recommendation classification, both with respect to strong and weak labels, and to all labels of the unified scheme. An error analysis indicates that, while there is a strong relationship between lexical choices and strength labels, there can be substantial variance in the choices made by different authors.

    M3 - Paper

    ER -

    Read J, Velldal E, Cavazza M, Georg G. A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations. 2016. Paper presented at 10th Language Resources and Evaluation Conference, Portorož, Slovenia.