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...

Applying document clustering techniques to multidocument summarization is a challenging problem, mostly because of the redundancy that exists in multiple sources. We compare several document clustering techniques for multi-document summarization in the NTCIR-4 TSC test collection. We conducted an experiment to evaluate the effectiveness of reducing redundancy in the production of summaries. Fro...

Existing multi-document summarization systems usually rely on a specific summarization model (i.e., a summarization method with a specific parameter setting) to extract summaries for different document sets with different topics. However, according to our quantitative analysis, none of the existing summarization models can always produce high-quality summaries for different document sets, and e...

While most people have a clear idea of what a single document summary should look like, this is not immediately obvious for a multidocument summary. There are many new questions to answer concerning the amount of documents to be summarized, the type of documents, the kind of summary that should be generated, the way the summary gets presented to the user, etc. The many approaches possible to mu...

Abstractive summarization is the ultimate goal of document summarization research, but previously it is less investigated due to the immaturity of text generation techniques. Recently impressive progress has been made to abstractive sentence summarization using neural models. Unfortunately, attempts on abstractive document summarization are still in a primitive stage, and the evaluation results...

Most of the existing multi-document summarization methods decompose the documents into sentences and work directly in the sentence space using a term-sentence matrix. However, the knowledge on the document side, i.e. the topics embedded in the documents, can help the context understanding and guide the sentence selection in the summarization procedure. In this paper, we propose a new Bayesian s...

Automatic document summarization has become increasingly important due to the quantity of written material generated worldwide. Generating good quality summaries enables users to cope with larger amounts of information. English-document summarization is a difficult task. Yet it is not sufficient. Environmental, economic, and other global issues make it imperative for English speakers to underst...