Sentence Ordering based on Cluster Adjacency in Multi-Document Summarization
نویسندگان
چکیده
In this paper, we propose a cluster-adjacency based method to order sentences for multi-document summarization tasks. Given a group of sentences to be organized into a summary, each sentence was mapped to a theme in source documents by a semi-supervised classification method, and adjacency of pairs of sentences is learned from source documents based on adjacency of clusters they belong to. Then the ordering of the summary sentences can be derived with the first sentence determined. Experiments and evaluations on DUC04 data show that this method gets better performance than other existing sentence ordering methods.
منابع مشابه
Sentence Clustering-based Summarization of Multiple Text Documents
With the rapid growth of the World Wide Web, information overload is becoming a problem for an increasingly large number of people. Automatic Multidocument summarization can be an indispensable solution to reduce the information overload problem on the web. This kind of summarization facility helps users to see at a glance what a collection is about and provides a new way of managing a vast hoa...
متن کاملSignificance of Sentence Ordering in Multi Document Summarization
Multi-document summarization represents the information in a concise and comprehensive manner. In this paper we discuss the significance of ordering of sentences in multi document summarization. We show experimental results on DUC2002 dataset. These results show the ordering of summaries before and, improvement in this, after applying sentence ordering. For this purpose we used a term frequency...
متن کاملSentence Ordering with Event-Enriched Semantics and Two-Layered Clustering for Multi-Document News Summarization
We propose an event-enriched model to alleviate the semantic deficiency problem in the IR-style text processing and apply it to sentence ordering for multi-document news summarization. The ordering algorithm is built on event and entity coherence, both locally and globally. To accommodate the eventenriched model, a novel LSA-integrated two-layered clustering approach is adopted. The experimenta...
متن کاملSentence ordering with manifold-based classification in multi-document summarization
In this paper, we propose a sentence ordering algorithm using a semi-supervised sentence classification and historical ordering strategy. The classification is based on the manifold structure underlying sentences, addressing the problem of limited labeled data. The historical ordering helps to ensure topic continuity and avoid topic bias. Experiments demonstrate that the method is effective.
متن کاملUsing Context Inference to Improve Sentence Ordering for Multi-document Summarization
In this paper, we propose a novel context inference-based approach for sentences ordering in mult i-document summarization application. Our method first detects whether or not two summarizat ion sentences should be adjacent according to the similarity between one summarizat ion sentence and the context of the other one, and then it computes the reliability of the adjacent summarization sentence...
متن کامل