Cross-language summarization is the task of generating a summary in a language different from the language of the source documents. In this paper, we propose a graph-based approach to multi-document summarization that integrates machine translation quality scores in the sentence extraction process. We evaluate our method on a manually translated subset of the DUC 2004 evaluation campaign. Resul...

For the update summarization task of TAC 2011, we submitted two runs applying a improved graph-based sentence ranking method. The difference between these two runs is that the second one aims to acquire the category words and use them for extracting information-rich sentences. For the update summarization task, we adopt similar methods used in previous evaluations and simultaneously penalize th...

Large-scale, highly-interconnected networks pervade our society and the natural world around us, including the World Wide Web, social networks, knowledge graphs, genome and scientific databases, medical and government records. The massive scale of graph data often surpasses the available computation and storage resources. Besides, users get overwhelmed by the daunting task of understanding and ...

We propose a method for achieving a novel concise graph-based representation for retrieval of objects from large video data. The emphasis in this paper is towards achieving a compact representation of video data for faster retrieval. Specifically, we use information available from scripts and subtitles in order to group all occurrences of an object in video data, which provides a separate repre...

Graph-based ranking algorithm has been recently exploited for summarization by using sentence-to-sentence relationships. Given a document set with linkage information to summarize, different sentences belong to different documents or clusters (either visible cluster via anchor texts or invisible cluster by semantics), which enables a hierarchical structure. It is challenging and interesting to ...

The graph-based ranking algorithm has been recently exploited for multi-document summarization by making only use of the sentence-to-sentence relationships in the documents, under the assumption that all the sentences are indistinguishable. However, given a document set to be summarized, different documents are usually not equally important, and moreover, different sentences in a specific docum...

Multi-document summarization is a process of automatic creation of a compressed version of the given collection of documents. Recently, the graph-based models and ranking algorithms have been extensively researched by the extractive document summarization community. While most work to date focuses on sentence-level relations in this paper we present graph model that emphasizes not only sentence...

We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use ...

Abstractive dialogue summarization is the task of capturing highlights a and rewriting them into concise version. In this paper, we present novel multi-speaker summarizer to demonstrate how large-scale commonsense knowledge can facilitate understanding summary generation. detail, consider utterance as two different types data design Dialogue Heterogeneous Graph Network (D-HGN) for modeling both...