Multi-document summarization

About: Multi-document summarization is a research topic. Over the lifetime, 2270 publications have been published within this topic receiving 71850 citations.

Extractive Text Summarization

Abstract: Text summarization helps in reducing the size of a text while preserving its information content. In this paper, a text summarization approach is proposed based on removal of redundant sentences. Initially, each sentence from original text (input) is scored based on how much redundant the sentence is and at what extent that sentence is able to cover other sentences by itself. This approach is best effective on the documents which are highly redundant and contain repetitive opinions about a topic. The summarization takes places in two stages wherein the input of a stage is the output of previous stage and after each stage the output summary is less redundant than the previous one.

Summarizing Scientific Texts: Experiments with Extractive Summarizers

Abstract: In this paper we present experiments on scientific text summarization. From a complete text, we produce a shorter version containing all the main parts of the research. Having in mind the sophisticated structure of such texts, we show that good results can be achieved using simple extractive summarizers with some obvious improvements that consider the specificity of the text genre. Specifically, we enhance the summarization process with the ability to detect and appropriately treat the text structure.

ViMs: a high-quality Vietnamese dataset for abstractive multi-document summarization

Abstract: Automatic text summarization is important in this era due to the exponential growth of documents available on the Internet In the Vietnamese language, VietnameseMDS is the only publicly available dataset for this task Although the dataset has 199 clusters, there are only three documents in each cluster, which is small compared to typical datasets in English This motivates us to construct ViMs—a big and high-quality Vietnamese dataset for abstractive multi-document summarization To that end, we recruited 29 annotators and enhanced MDSWriter—an open-source annotation tool, to support the annotators in creating gold standard summaries As a result, ViMs has 600 summaries corresponding to 300 clusters of 1,945 documents We have verified the reliability of our dataset by using a variety of metrics including conventional Cohen’s $$\kappa $$ , relaxed Cohen’s $$\kappa $$ —a new metric that we propose to make it more suitable for abstractive summarization, and ROUGE scores A relaxed $$\kappa $$ score of 055 indicate that ViMs could attain moderate agreement between annotators Meanwhile, ROUGE scores are 0729 of ROUGE-1, 0507 of ROUGE-2 and 0524 of ROUGE-SU4 We have further evaluated ViMs by using three different summarization systems: TextRank, CFVi and MUSEEC Their performances are 0628, 0711 and 0732 of ROUGE-1, respectively These results show that the ViMs dataset is suitable for both training and evaluating multi-document summarization systems We have made the dataset and evaluation results of this work publicly available for research community It is noted that unlike previous work that only published the final summarization dataset, we also publish intermediate annotation results, which can be used in other NLP problems such as sentence classification