We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS). Extractive TS relies on the concept of sentence salience to identify the most important sentences in a document or set of documents. Salience is typically defined in terms of the presence of particular important words or in terms of similarity to a centroid pseudo-sentence. We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences. In this model, a connectivity matrix based on intra-sentence cosine similarity is used as the adjacency matrix of the graph representation of sentences. Our system, based on LexRank ranked in first place in more than one task in the recent DUC 2004 evaluation. In this paper we present a detailed analysis of our approach and apply it to a larger data set including data from earlier DUC evaluations. We discuss several methods to compute centrality using the similarity graph. The results show that degree-based methods (including LexRank) outperform both centroid-based methods and other systems participating in DUC in most of the cases. Furthermore, the LexRank with threshold method outperforms the other degree-based techniques including continuous LexRank. We also show that our approach is quite insensitive to the noise in the data that may result from an imperfect topical clustering of documents. 1.

The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document summarization can be determined from the ordering of sentences in the input article, this is not the case for multidocument summarization where summary sentences may be drawn from different input articles. In this paper, we propose a methodology for studying the properties of ordering information in the news genre and describe experiments done on a corpus of multiple acceptable orderings we developed for the task. Based on these experiments, we implemented a strategy for ordering information that combines constraints from chronological order of events and topical relatedness. Evaluation of our augmented algorithm shows a significant improvement of the ordering over two baseline strategies. 1.

We discuss technology to help a person monitor changes in news coverage over time. We define temporal summaries of news stories as extracting a single sentence from each event within a news topic, where the stories are presented one at a time and sentences from a story must be ranked before the next story can be considered. We explain a method for evaluation, and describe an evaluation corpus that we have built. We also propose several methods for constructing temporal summaries and evaluate their effectiveness in comparison to degenerate cases. We show that simple approaches are effective, but that the problem is far from solved. Keywords Summarization, Experimental Design and Metrics 1.

We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS). Extractive TS relies on the concept of sentence salience to identify the most important sentences in a document or set of documents. Salience is typically defined in terms of the presence of particular important words or in terms of similarity to a centroid pseudo-sentence. We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences. In this model, a connectivity matrix based on intra-sentence cosine similarity is used as the adjacency matrix of the graph representation of sentences. Our system, based on LexRank ranked in first place in more than one task in the recent DUC 2004 evaluation. In this paper we present a detailed analysis of our approach and apply it to a larger data set including data from earlier DUC evaluations. We discuss several methods to compute centrality using the similarity graph. The results show that degree-based methods (including LexRank) outperform both centroid-based methods and other systems participating in DUC in most of the cases. Furthermore, the LexRank with threshold method outperforms the other degree-based techniques including continuous LexRank. We also show that our approach is quite insensitive to the noise in the data that may result from an imperfect topical clustering of documents. 1.

A system that can produce informative summaries, highlighting common information found in many online documents, will help Web users to pinpoint information that they need without extensive reading. In this article, we introduce sentence fusion, a novel text-to-text generation technique for synthesizing common information across documents. Sentence fusion involves bottom-up local multisequence alignment to identify phrases conveying similar information and statistical generation to combine common phrases into a sentence. Sentence fusion moves the summarization field from the use of purely extractive methods to the generation of abstracts that contain sentences not found in any of the input documents and can synthesize information across sources. 1.

This paper discusses passage extraction approaches to multidocument summarization that use available information about the document set as a whole and the relationships between the documents to build on single document summarization methodology. Multi-document summarization differs from single in that the issues of compression, speed, redundancy and passage selection are critical in the formation of useful summaries, as well as the user's goals in creating the summary. Our approach addresses these issues by using domain-independent techniques based mainly on fast, statistical processing, a metric for reducing redundancy and maximizing diversity in the selected passages, and a modular framework to allow easy parameterization for different genres, corpora characteristics and user requirements. We examined howhumans create multi-document summaries as well as the characteristics of such summaries and use these summaries to evaluate the performance of various multidocument summarization algorithms. 1.

Human variation in content selection in summarization has given rise to some fundamental research questions: How can one incorporate the observed variation in suitable evaluation measures? How can such measures reflect the fact that summaries conveying different content can be equally good and informative? In this paper we address these very questions by proposing a method for analysis of multiple human abstracts into semantic content units. Such analysis allows us not only to quantify human variation in content selection, but also to assign empirical importance weight to different content units. It serves as the basis for an evaluation method, the Pyramid Method, that incorporates the observed variation and is predictive of different equally informative summaries. We discuss the reliability of content unit annotation, the properties of Pyramid scores, and their correlation with other evaluation methods.

Accessing an ever increasing number of emails, possibly on small mobile devices, has become a major problem for many users. Email summarization is a promising way to solve this problem. In this paper, we propose a new framework for email summarization. One novelty is to use a fragment quotation graph to try to capture an email conversation. The second novelty is to use clue words to measure the importance of sentences in conversation summarization. Based on clue words and their scores, we propose a method called CWS, which is capable of producing a summary of any length as requested by the user. We provide a comprehensive comparison of CWS with various existing methods on the Enron data set. Preliminary results suggest that CWS provides better summaries than existing methods.

As the amount of on-line information increases, systems that can automatically summarize one or more documents become increasingly desirable. Recent research has investigated types of summaries, methods to create them, and methods to evaluate them. Several evaluation competitions (in the style of the National Institute of Standards and Technology's [NIST's] Text Retrieval Conference [TREC]) have helped determine baseline performance levels and provide a limited set of training material. Frequent workshops and symposia reflect the ongoing interest of researchers around the world. The volume of papers edited by Mani and Maybury (1999) and a book (Mani 2001) provide good introductions to the state of the art in this rapidly evolving subfield. A summary can be loosely defined as a text that is prod

Hierarchies provide a means of organizing, summarizing and accessing information. We describe a method for automatically generating hierarchies from small collections of text, and then apply this technique to summarizing the documents retrieved by a search engine. We show that these hierarchies provide better access to the documents than a simple ranked list and that the terms in the hierarchy are better summaries of the documents than the top TF.IDF weighted terms. In addition, we discuss the formal framework of the technique and how the technique has been used with news databases and TREC collections.