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.

A System to Adapt Techniques of Text Summarizing to Polish.

Abstract: This paper describes a system, in which various methods of text summarizing can be adapted to Polish. A structure of the system is presented. A modular construction of the system and access to the system via the Internet are signaled. Keywords—Automatic summary generation, linguistic analysis, text generation.

DynE: Dynamic Ensemble Decoding for Multi-Document Summarization.

Abstract: Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing. However, some applications, such as multi-document summarization, multi-modal machine translation, and the automatic post-editing of machine translation, require mapping a set of multiple distinct inputs into a single output sequence. Recent work has introduced bespoke architectures for these multi-input settings, and developed models which can handle increasingly longer inputs; however, the performance of special model architectures is limited by the available in-domain training data. In this work we propose a simple decoding methodology which ensembles the output of multiple instances of the same model on different inputs. Our proposed approach allows models trained for vanilla s2s tasks to be directly used in multi-input settings. This works particularly well when each of the inputs has significant overlap with the others, as when compressing a cluster of news articles about the same event into a single coherent summary, and we obtain state-of-the-art results on several multi-document summarization datasets.

An interactive personalized video summarization based on sketches

Abstract: Video summarization aims to give a condensed presentation of video content, facilitating users to efficiently and effectively browse videos and obtain specific information in a short time following users' attention. In this paper, we propose a novel method to generate personalized sketch summarization supporting sketch interaction that is characterized for being coherent, compact and interactive, allowing to measure how event tracks following the spatio-temporal progress and how users directly interact with the content of video. The stylized algorithm is provided to obtain sketches from key-frames and a graph is constructed representing attributes of sketches. Thus a layout algorithm based on graph is presented for generating sketch summarization. Furthermore, efficient interaction on sketch video summarization is provided. Finally, user experience shows that the proposed sketch summarization helps users quickly grasp the specific information, understand the context and interact with the content of interest.

Automatic multi-document summarization for Indonesian documents using hybrid abstractive-extractive summarization technique

Abstract: This paper discusses the development of multi-document summarization for Indonesian documents by using hybrid abstractive-extractive summarization approach. Multi-document summarization is a technology that able to summarize multiple documents and present them in one summary. The method used in this research, hybrid abstractive-extractive summarization technique, is a summarization technique that is the combination of WordNet based text summarization (abstractive technique) and title word based text summarization (extractive technique). After an experiment with LSA as the comparison method, this research method successfully generated a well-compressed and readable summary with a fast processing time.

A reinforcement learning framework for answering complex questions

Abstract: Scoring sentences in documents given abstract summaries created by humans is important in extractive multi-document summarization. In this paper, we use extractive multi-document summarization techniques to perform complex question answering and formulate it as a reinforcement learning problem. We use a reward function that measures the relatedness of the candidate (machine generated) summary sentences with abstract summaries. In the training stage, the learner iteratively selects original document sentences to be included in the candidate summary, analyzes the reward function and updates the related feature weights accordingly. The final weights found in this phase are used to generate summaries as answers to complex questions given unseen test data. We use a modified linear, gradient-descent version of Watkins' Q(») algorithm with µ-greedy policy to determine the best possible action i.e. selecting the most important sentences. We compare the performance of this system with a Support Vector Machine (SVM) based system. Evaluation results show that the reinforcement method advances the SVM system improving the ROUGE scores by