this paper we argue that scientific articles require a different summarization strategy than, for instance, news articles. We propose a strategy which concentrates on the rhetorical status of statements in the article: Material for summaries is selected in such a way that summaries can highlight the new contribution of the source paper and situate it with respect to earlier work. We provide a gold standard for summaries of this kind consisting of a substantial corpus of conference articles in computational linguistics with human judgements of rhetorical status and relevance. We present several experiments measuring our judges' agreement on these annotations. We also present an algorithm which, on the basis of the annotated training material, selects content and classifies it into a fixed set of seven rhetorical categories. The output of this extraction and classification system can be viewed as a single-document summary in its own right; alternatively, it can be used to generate task-oriented and user-tailored summaries designed to give users an overview of a scientific field.

@article{Teufel02summarizingscientific, author = {Teufel, Simone and Moens, Marc}, title = {Summarizing Scientific Articles - Experiments with Relevance and Rhetorical Status}, journal = {Computational Linguistics}, year = {2002}, volume = {28}, pages = {2002}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.27.5593}, keywords = {articles, relevance, scientific, sota, summarizing}, abstract = {this paper we argue that scientific articles require a different summarization strategy than, for instance, news articles. We propose a strategy which concentrates on the rhetorical status of statements in the article: Material for summaries is selected in such a way that summaries can highlight the new contribution of the source paper and situate it with respect to earlier work. We provide a gold standard for summaries of this kind consisting of a substantial corpus of conference articles in computational linguistics with human judgements of rhetorical status and relevance. We present several experiments measuring our judges' agreement on these annotations. We also present an algorithm which, on the basis of the annotated training material, selects content and classifies it into a fixed set of seven rhetorical categories. The output of this extraction and classification system can be viewed as a single-document summary in its own right; alternatively, it can be used to generate task-oriented and user-tailored summaries designed to give users an overview of a scientific field.} }

%0 = article %A = Teufel, Simone and Moens, Marc %D = 2002 %T = Summarizing Scientific Articles - Experiments with Relevance and Rhetorical Status %U = http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.27.5593