We model document summarization as a nonlinear 0-1 programming problem where an objective function is defined as Heronian mean of the objective functions enforcing the coverage and diversity. The proposed model implemented on a multi-document summarization task. Experiments on DUC2001 and DUC2002 datasets showed that the proposed model outperforms the other summarization methods. Index Terms – ...

Multi-document summarization has been used for extracting the most relevant sentences from a set of documents, allowing the user to more quickly address the content thereof. This paper addresses the generation of extractive summaries from multiple documents as a binary optimization problem and proposes a method, based on CHC evolutionary algorithm and greedy search, called MA-MultiSumm, in whic...

In this paper, we describe the following two approaches to summarization: (1) only sentence extraction, (2) sentence extraction + bunsetsu elimination. For both approaches, we use the machine learning algorithm called Support Vector Machines. We participated in both Task-A (single-document summarization task) and Task-B (multi-document summarization task) of TSC-2.

Abstract We have introduced information extraction technique such as named entity tagging and pattern discovery to a summarization system based on sentence extraction technique, and evaluated the performance in the Document Understanding Conference 2001 (DUC-2001). We participated in the Single Document Summarization task in DUC-2001 and achieved one of the best performance in subjective evalua...

Although recent years has seen increased and successful research efforts in the areas of single -document summarization, multi-document summarization, and information extraction, very few investigations have explored the potential of merging summarization and information extraction techniques. This paper presents and evaluates the initial version of RIPTIDES, a system that combines information ...

The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets. We present two QMDS datasets, which we construct using data augmentation methods: (1) transferring commonly used single-document CNN/Daily Mail summarization dataset to create QMDSCNN dataset, and (2) mining search-query logs QMDSIR dataset. The...

Traditional approaches to extractive summarization rely heavily on humanengineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor. This architecture allows us to develop different classe...

We present our state of the art multilingual text summarizer capable of single as well as multi-document text summarization. The algorithm is based on repeated application of TextRank on a sentence similarity graph, a bag of words model for sentence similarity and a number of linguistic preand post-processing steps using standard NLP tools. We submitted this algorithm for two different tasks of...