El-Kilany, A., and I. Saleh, "Unsupervised document summarization using clusters of dependency graph nodes", Intelligent Systems Design and Applications (ISDA), 2012 12th International Conference on, Kochi,India, IEEE, pp. 557-561, 2012. Abstractunsupervised_document_summarization_using_clusters_of_dependency_graph_-_isda_2012.pdf

In this paper, we investigate the problem of extractive single document summarization. We propose an unsupervised summarization method that is based on extracting and scoring keywords in a document and using them to find the sentences that best represent its content. Keywords are extracted and scored using clustering and dependency graphs of sentences. We test our method using different corpora including news, events and email corpora. We evaluate our method in the context of news summarization and email summarization tasks and compare the results with previously published ones.

El-Kilany, A. R., S. R. El-Beltagy, and M. E. El-Sharkawi, "Sentence Compression via Clustering of Dependency Graph Nodes", 8th International Conference on Natural Language Processing and Knowledge Engineering(NLP-KE'12), Hefei(HuangShan),China, 20-24 September, 2012. Abstractsentence_compression_via_clustering__of_dependency_graph_nodes-nlpke_2012.pdf

Sentence compression is the process of removing words or phrases from a sentence in a
manner that would abbreviate the sentence while conserving its original meaning. This work
introduces a model for sentence compression based on dependency graph clustering. The main
idea of this work is to cluster related dependency graph nodes in a single chunk, and to then
remove the chunk which has the least significant effect on a sentence. The proposed model
does not require any training parallel corpus. Instead, it uses the grammatical structure graph
of the sentence itself to find which parts should be removed. The paper also presents the
results of an experiment in which the proposed work was compared to a recent supervised
technique and was found to perform better.