Multi-document update summarisation using co-related terms for scientific articles and news group

In the current trend, as the information on the internet is exploding exponentially in the course of time, and as nearly 90% of information is stored in the form of text, we need an effective and concise approach to help the user to locate the main points from the document corpus. Thus, there arises a need to provide a high quality summary in order to allow the user to quickly locate the desired information from the document clusters. Our proposed work deals with a new summarisation technique named as multi-document update summarisation based on co-related terms, considering terms and their related terms as concepts for identifying interrelated concepts from the documents of the dynamic clusters. Update summarisation is achieved by two methods: 1) static approach; 2) dynamic approach. We have also addressed the sentence reordering and redundancy elimination technique based on concepts to improve the efficiency of the summary. The proposed dynamic updation of summary is compared with the existing COBWEB update summarisation algorithm considering scientific articles and news tracks as dataset. From the analysis it is inferred that our proposed approach gives better results considering F-measure as the performance metric.