Article Structure
Abstract
In citation-based summarization, text written by several researchers is leveraged to identify the important aspects of a target paper.
Introduction
Scientific research is a cumulative activity.
Related Work
The idea of analyzing and utilizing citation information is far from new.
Motivation
The coherence and readability of citation-based summaries are impeded by several factors.
Approach
In this section we describe a system that takes a scientific paper and a set of citation sentences that cite it as input, and outputs a citation summary of the paper.
Evaluation
We provide three levels of evaluation.
Conclusions
In this paper, we presented a new approach for citation-based summarization of scientific papers
Topics
SVM
- We use Support Vector Machines ( SVM ) with linear kernel as our classifier.Page 4, “Approach”
- We use SVM with linear kernel as our classifier.Page 4, “Approach”
- Sentence Filtering Evaluation: We used Support Vector Machines ( SVM ) with linear kernel as our classifier.Page 7, “Evaluation”
- Sentence Classification Evaluation: We used SVM in this step as well.Page 7, “Evaluation”
- Author Name Replacement Evaluation: The classifier used in this task is also SVM .Page 7, “Evaluation”
See all papers in Proc. ACL 2011 that mention SVM.
See all papers in Proc. ACL that mention SVM.
Back to top.
cross validation
- We performed 10-fold cross validation on the labeled sentences (unsuitable vs all other categories) in dataset] .Page 7, “Evaluation”
- We also performed 10-fold cross validation on the labeled sentences (the five functional categories).Page 7, “Evaluation”
- We performed 10-fold cross validation on the labeled sentences of dataset] .Page 7, “Evaluation”
See all papers in Proc. ACL 2011 that mention cross validation.
See all papers in Proc. ACL that mention cross validation.
Back to top.
machine learning
- We use a machine learning technique for this purpose.Page 4, “Approach”
- We classify the citation sentences into the five categories mentioned above using a machine learning technique.Page 4, “Approach”
- To determine whether a reference is part of the sentence or not, we again use a machine learning approach.Page 6, “Approach”
See all papers in Proc. ACL 2011 that mention machine learning.
See all papers in Proc. ACL that mention machine learning.
Back to top.
parse tree
- Figure 1 shows a portion of the parse tree for Sentence (1) (from Section 1).Page 4, “Approach”
- We extract the scope of the reference from the parse tree as follows.Page 4, “Approach”
- For example, the parse tree shown in Figure 1 suggests that the scope of the reference is:Page 4, “Approach”
See all papers in Proc. ACL 2011 that mention parse tree.
See all papers in Proc. ACL that mention parse tree.
Back to top.
