Many methods, including supervised and unsupervised algorithms, have been developed for extractive document summarization. Most supervised methods consider the summarization task as a twoclass classification problem and classify each sentence individually without leveraging the relationship among sentences. The unsupervised methods use heuristic rules to select the most informative sentences into a summary directly, which are hard to generalize. In this paper, we present a Conditional Random Fields (CRF) based framework to keep the merits of the above two kinds of approaches while avoiding their disadvantages. What is more, the proposed framework can take the outcomes of previous methods as features and seamlessly integrate them. The key idea of our approach is to treat the summarization task as a sequence labeling problem. In this view, each document is a sequence of sentences and the summarization procedure labels the sentences by 1 and 0. The label of a sentence depends on the assignment of labels of others. We compared our proposed approach with eight existing methods on an open benchmark data set. The results show that our approach can improve the performance by more than 7.1 % and 12.1 % over the best supervised baseline and unsupervised baseline respectively in terms of two popular metrics F1 and ROUGE-2. Detailed analysis of the improvement is presented as well. 1

Abstract not found

This paper investigates the automatic evaluation of text coherence for machine-generated texts. We introduce a fully-automatic, linguistically rich model of local coherence that correlates with human judgments. Our modeling approach relies on shallow text properties and is relatively inexpensive. We present experimental results that assess the predictive power of various discourse representations proposed in the linguistic literature. Our results demonstrate that certain models capture complementary aspects of coherence and thus can be combined to improve performance. 1

We have explored the usefulness of incorporating speech and discourse features in an automatic speech summarization system applied to meeting recordings from the ICSI Meetings corpus. By analyzing speaker activity, turn-taking and discourse cues, we hypothesize that such a system can outperform solely text-based methods inherited from the field of text summarization. The summarization methods are described, two evaluation methods are applied and compared, and the results clearly show that utilizing such features is advantageous and efficient. Even simple methods relying on discourse cues and speaker activity can outperform text summarization approaches. 1.

Most previous Web-page summarization methods treat a Web page as plain text. However, such methods fail to uncover the full knowledge associated with a Web page to build a high-quality summary, because the Web contains many hidden relationships that are not used in these methods. Uncovering the inherent knowledge is important to building good Web-page summarizers. In this paper, we extract the extra knowledge from the clickthrough data of a Web search engine to improve Web-page summarization. We first analyze the feasibility to utilize clickthrough data in text summarization, and then propose two adapted summarization methods that take advantage of the relationships discovered from the clickthrough data. For those pages not covered by the clickthrough data, we put forward a thematic lexicon approach to generate implicit knowledge for them. Our methods are evaluated on a relatively small dataset consisting of manually annotated pages as well as a large dataset that is crawled from the Open Directory Project website. The experimental results indicate that significant improvements can be achieved through our proposed summarizer as compared with summarizers without using the clickthrough data. Categories and Subject Descriptors H.4 [Information Systems Applications]: Miscellaneous; I.5.4 [Pattern Recognition]: Applications—Text processing

Recent research has shown that a balanced harmonic mean (F1 measure) of unigram precision and recall outperforms the widely used BLEU and NIST metrics for Machine Translation evaluation in terms of correlation with human judgments of translation quality. We show that significantly better correlations can be achieved by placing more weight on recall than on precision. While this may seem unexpected, since BLEU and NIST focus on n-gram precision and disregard recall, our experiments show that correlation with human judgments is highest when almost all of the weight is assigned to recall. We also show that stemming is significantly beneficial not just to simpler unigram precision and recall based metrics, but also to BLEU and NIST.

Topic-focused multi-document summarization aims to produce a summary biased to a given topic or user profile. This paper presents a novel extractive approach based on manifold-ranking of sentences to this summarization task. The manifold-ranking process can naturally make full use of both the relationships among all the sentences in the documents and the relationships between the given topic and the sentences. The ranking score is obtained for each sentence in the manifold-ranking process to denote the biased information richness of the sentence. Then the greedy algorithm is employed to impose diversity penalty on each sentence. The summary is produced by choosing the sentences with both high biased information richness and high information novelty. Experiments on DUC2003 and DUC2005 are performed and the ROUGE evaluation results show that the proposed approach can significantly outperform existing approaches of the top performing systems in DUC tasks and baseline approaches. 1

Most approaches to extractive summarization define a set of features upon which selection of sentences is based, using algorithms independent of the features themselves. We propose a new set of features based on low-level, atomic events that describe relationships between important actors in a document or set of documents. We investigate the effect this new feature has on extractive summarization, compared with a baseline feature set consisting of the words in the input documents, and with state-of-the-art summarization systems. Our experimental results indicate that not only the event-based features offer an improvement in summary quality over words as features, but that this effect is more pronounced for more sophisticated summarization methods that avoid redundancy in the output. 1

The usual approach for automatic summarization is sentence extraction, where key sentences from the input documents are selected based on a suite of features. While word frequency often is used as a feature in summarization, its impact on system performance has not been isolated. In this paper, we study the contribution to summarization of three factors related to frequency: content word frequency, composition functions for estimating sentence importance from word frequency, and adjustment of frequency weights based on context. We carry out our analysis using datasets from the Document Understanding Conferences, studying not only the impact of these features on automatic summarizers, but also their role in human summarization. Our research shows that a frequency based summarizer can achieve performance comparable to that of state-of-the-art systems, but only with a good composition function; context sensitivity improves performance and significantly reduces repetition.

Abstract. In this work we study the theoretical and empirical properties of various global inference algorithms for multi-document summarization. We start by defining a general framework and proving that inference in it is NP-hard. We then present three algorithms: The first is a greedy approximate method, the second a dynamic programming approach based on solutions to the knapsack problem, and the third is an exact algorithm that uses an Integer Linear Programming formulation of the problem. We empirically evaluate all three algorithms and show that, relative to the exact solution, the dynamic programming algorithm provides near optimal results with preferable scaling properties. 1