We present results from evaluations of an automatic text summarization technique that uses a combination of Random Indexing and PageRank. In our experiments we use two types of texts: news paper texts and government texts. Our results show that text type as well as other aspects of texts of the same type influence the performance. Combining PageRank and Random Indexing provides the best results...

In this paper, we introduce a large-scale test collection for multiple document summarization, the Text Summarization Challenge 3 (TSC3) corpus. We detail the corpus construction and evaluation measures. The significant feature of the corpus is that it annotates not only the important sentences in a document set, but also those among them that have the same content. Moreover, we define new eval...

We have constructed an integrated web-based system for collection of extract-based corpora and for evaluation of summaries and summarization systems. During evaluation and examination of the collected and generated data we found that in a situation of low agreement among the informants the corpus gives unduly favors to summarization systems that use sentence position as a central weighting feat...

Automatic summarization can help users extract the most important pieces of information from the vast amount of text digitized into electronic form everyday. Central to automatic summarization is the notion of similarity between sentences in text. In this paper we propose the use of continuous vector representations for semantically aware representations of sentences as a basis for measuring si...

Update summarization is an extension of query-focused multidocument summarization which was launched at DUC 2007. The essential problem of update summarization is to attain the information novelty and topic continuity simultaneously. In this paper, we proposed several Temporal Content Filtering Methods to extract the time-varying information for the update summarization task, while the topic co...

In recent years, there has been increased interest in topic-focused multi-document summarization. In this task, automatic summaries are produced in response to a specific information request, or topic, stated by the user. The system we have designed to accomplish this task comprises four main components: a generic extractive summarization system, a topic-focusing component, sentence simplificat...

Update summarization is an emerging summarization task of creating a short summary of a set of news articles, under the assumption that the user has already read a given set of earlier articles. In this paper, we propose a new co-ranking method to address the update summarization task. The proposed method integrates two co-ranking processes by adding strict constraints. In comparison with the o...

Although there has been a great deal of research on automatic summarization, most methods are based on a statistical approach, disregarding relationships between extracted textual segments. To ensure sentence connectivity, we propose a novel method to extract a set of comprehensible sentences that centers on several key points. This method generates a similarity network from documents with a le...

We introduce the novel problem of automatic related work summarization. Given multiple articles (e.g., conference/journal papers) as input, a related work summarization system creates a topic-biased summary of related work specific to the target paper. Our prototype Related Work Summarization system, ReWoS, takes in set of keywords arranged in a hierarchical fashion that describes a target pape...

This paper presents LIC2M’s second participation in TAC evaluation campaign (Update Summarization task). Two runs were submitted: simple summarization through sense concentration and combined summarization through sense concentration and Contextual Exploration rules. The sense concentration feature is based on the unsupervised recognition of word senses from a large corpus. Contextual Explorati...