A BE-based Multi-document Summarizer with Sentence Compression
نویسندگان
چکیده
This paper describes a multi-document summarizer based on basic elements (BE), head-modifier-relation representation of document content developed at ISI. To increase the coverage of automatically created summaries at a given length, we first generate a summary about twice of the intended length, then apply compression techniques to make sure the resulting summaries fall within the length constraint of target summaries. Our initial results show that the BE-based summarizer with compression achieved 0.0654 in BE-F score that was significantly better than the BE-F score of 0.0542 without compression.
منابع مشابه
Extraction Based Multi Document Summarization using Single Document Summary Cluster
Multi document summarization has very great impact among research community, ever since the growth of online information and availability. Selecting most important sentences from such huge repository of data is quiet tricky and challenging task. While multi document poses some additional overhead in sentence selection, generating summaries for each individual documents and merging the sentences...
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 کاملMUSEEC: A Multilingual Text Summarization Tool
The MUSEEC (MUltilingual SEntence Extraction and Compression) summarization tool implements several extractive summarization techniques – at the level of complete and compressed sentences – that can be applied, with some minor adaptations, to documents in multiple languages. The current version of MUSEEC provides the following summarization methods: (1) MUSE – a supervised summarizer, based on ...
متن کاملCentroid-based summarization of multiple documents
We present a multi-document summarizer, MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We describe two new techniques, a centroid-based summarizer, and an evaluation scheme based on sentence utility and subsumption. We have applied this evaluation to both single and multiple document summaries. Finally, we describe two user studies tha...
متن کاملA Query Focused Multi Document Automatic Summarization
The present paper describes the development of a query focused multi-document automatic summarization. A graph is constructed, where the nodes are sentences of the documents and edge scores reflect the correlation measure between the nodes. The system clusters similar texts having related topical features from the graph using edge scores. Next, query dependent weights for each sentence are adde...
متن کامل