The ability to convey relevant and diverse information is critical in multi-document summarization yet remains elusive for neural seq-to-seq models whose outputs are often redundant fail correctly cover important details. In this work, we propose an attention mechanism which encourages greater focus on relevance diversity. Attention weights computed based (proportional) probabilities given by D...

This paper describes a method for language independent extractive summarization that relies on iterative graph-based ranking algorithms. Through evaluations performed on a single-document summarization task for English and Portuguese, we show that the method performs equally well regardless of the language. Moreover, we show how a metasummarizer relying on a layered application of techniques fo...

Information overload becomes a serious problem in the digital age. It negatively impacts understanding of useful information. How to alleviate this problem is the main concern of research on natural language processing, especially multi-document summarization. With the aim of seeking a new method to help justify the importance of similar sentences in multi-document summarizations, this study pr...

For the blessing of World Wide Web, the corpus of online information is gigantic in its volume. Search engines have been developed such as Google, AltaVista, Yahoo, etc., to retrieve specific information from this huge amount of data. But the outcome of search engine is unable to provide expected result as the quantity of information is increasing enormously day by day and the findings are abun...

Automatic Multi-Document summarization is still hard to realize. Under such circumstances, we believe, it is important to observe how humans are doing the same task, and look around for different strategies. We prepared 100 document sets similar to the ones used in the DUC multi-document summarization task. For each document set, several people prepared the following data and we conducted a sur...