Summarizing Scientific Articles: Experiments with Relevance and Rhetorical Status
Резюмирование научных статей: эксперименты с релевантностью и риторическим статусом
2002-12-01
SCID: 54.1/92uv63fb
Discuss with AI
computational linguistics corpusrhetorical classificationrhetorical statusscientific article summarizationsentence relevance
Figures from the paper
Abstract (AI)
In this article we propose a strategy for the summarization of scientific articles that concentrates on the rhetorical status of statements in an article: Material for summaries is selected in such a way that summaries can highlight the new contribution of the source article 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 annotated with human judgments of the rhetorical status and relevance of each sentence in the articles. We present several experiments measuring our judges' agreement on these annotations. We also present an algorithm that, on the basis of the annotated training material, selects content from unseen articles 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 provides starting material for the generation of task-oriented and user-tailored summaries designed to give users an overview of a scientific field.
Key Findings
1
A trained algorithm selects content from unseen articles and classifies it into seven fixed rhetorical categories.
2
Experiments measure annotator agreement for the relevance and rhetorical-status annotations, establishing their consistency as a gold standard.
3
It introduces a substantial corpus of computational linguistics conference papers annotated with human judgments of sentence relevance and rhetorical status.
4
The paper proposes scientific summarization centered on rhetorical status to emphasize an article’s novel contribution and relationship to prior work.
5
The resulting extraction and classification can serve as single-document summaries or as input for task-oriented and user-tailored scientific summaries.
Research Object
Scientific articles in computational linguistics (conference papers) annotated with sentence-level rhetorical status and relevance
Research Subject
rhetorical status and relevance of statements for selecting and classifying summary content
Publication Details
Publication Date
2002-12-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest