首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 62 毫秒
1.
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 simplification, and lexical expansion of topic words. This paper details each of these components, together with experiments designed to quantify their individual contributions. We include an analysis of our results on two large datasets commonly used to evaluate task-focused summarization, the DUC2005 and DUC2006 datasets, using automatic metrics. Additionally, we include an analysis of our results on the DUC2006 task according to human evaluation metrics. In the human evaluation of system summaries compared to human summaries, i.e., the Pyramid method, our system ranked first out of 22 systems in terms of overall mean Pyramid score; and in the human evaluation of summary responsiveness to the topic, our system ranked third out of 35 systems.  相似文献   

2.
The rise in the amount of textual resources available on the Internet has created the need for tools of automatic document summarization. The main challenges of query-oriented extractive summarization are (1) to identify the topics of the documents and (2) to recover query-relevant sentences of the documents that together cover these topics. Existing graph- or hypergraph-based summarizers use graph-based ranking algorithms to produce individual scores of relevance for the sentences. Hence, these systems fail to measure the topics jointly covered by the sentences forming the summary, which tends to produce redundant summaries. To address the issue of selecting non-redundant sentences jointly covering the main query-relevant topics of a corpus, we propose a new method using the powerful theory of hypergraph transversals. First, we introduce a new topic model based on the semantic clustering of terms in order to discover the topics present in a corpus. Second, these topics are modeled as the hyperedges of a hypergraph in which the nodes are the sentences. A summary is then produced by generating a transversal of nodes in the hypergraph. Algorithms based on the theory of submodular functions are proposed to generate the transversals and to build the summaries. The proposed summarizer outperforms existing graph- or hypergraph-based summarizers by at least 6% of ROUGE-SU4 F-measure on DUC 2007 dataset. It is moreover cheaper than existing hypergraph-based summarizers in terms of computational time complexity.  相似文献   

3.
The paper presents a study investigating the effects of incorporating novelty detection in automatic text summarisation. Condensing a textual document, automatic text summarisation can reduce the need to refer to the source document. It also offers a means to deliver device-friendly content when accessing information in non-traditional environments. An effective method of summarisation could be to produce a summary that includes only novel information. However, a consequence of focusing exclusively on novel parts may result in a loss of context, which may have an impact on the correct interpretation of the summary, with respect to the source document. In this study we compare two strategies to produce summaries that incorporate novelty in different ways: a constant length summary, which contains only novel sentences, and an incremental summary, containing additional sentences that provide context. The aim is to establish whether a summary that contains only novel sentences provides sufficient basis to determine relevance of a document, or if indeed we need to include additional sentences to provide context. Findings from the study seem to suggest that there is only a minimal difference in performance for the tasks we set our users and that the presence of contextual information is not so important. However, for the case of mobile information access, a summary that contains only novel information does offer benefits, given bandwidth constraints.  相似文献   

4.
Automatic document summarization using citations is based on summarizing what others explicitly say about the document, by extracting a summary from text around the citations (citances). While this technique works quite well for summarizing the impact of scientific articles, other genres of documents as well as other types of summaries require different approaches. In this paper, we introduce a new family of methods that we developed for legal documents summarization to generate catchphrases for legal cases (where catchphrases are a form of legal summary). Our methods use both incoming and outgoing citations, and we show how citances can be combined with other elements of cited and citing documents, including the full text of the target document, and catchphrases of cited and citing cases. On a legal summarization corpus, our methods outperform competitive baselines. The combination of full text sentences and catchphrases from cited and citing cases is particularly successful. We also apply and evaluate the methods on scientific paper summarization, where they perform at the level of state-of-the-art techniques. Our family of citation-based summarization methods is powerful and flexible enough to target successfully a range of different domains and summarization tasks.  相似文献   

5.
Some of the most popular measures to evaluate information filtering systems are usually independent of the users because they are based in relevance judgments obtained from experts. On the other hand, the user-centred evaluation allows showing the different impressions that the users have perceived about the system running. This work is focused on discussing the problem of user-centred versus system-centred evaluation of a Web content personalization system where the personalization is based on a user model that stores long term (section, categories and keywords) and short term interests (adapted from user provided feedback). The user-centred evaluation is based on questionnaires filled in by the users before and after using the system and the system-centred evaluation is based on the comparison between ranking of documents, obtained from the application of a multi-tier selection process, and binary relevance judgments collected previously from real users. The user-centred and system-centred evaluations performed with 106 users during 14 working days have provided valuable data concerning the behaviour of the users with respect to issues such as document relevance or the relative importance attributed to different ways of personalization. The results obtained shows general satisfaction on both the personalization processes (selection, adaptation and presentation) and the system as a whole.  相似文献   

6.
A critical challenge for Web search engines concerns how they present relevant results to searchers. The traditional approach is to produce a ranked list of results with title and summary (snippet) information, and these snippets are usually chosen based on the current query. Snippets play a vital sensemaking role, helping searchers to efficiently make sense of a collection of search results, as well as determine the likely relevance of individual results. Recently researchers have begun to explore how snippets might also be adapted based on searcher preferences as a way to better highlight relevant results to the searcher. In this paper we focus on the role of snippets in collaborative web search and describe a technique for summarizing search results that harnesses the collaborative search behaviour of communities of like-minded searchers to produce snippets that are more focused on the preferences of the searchers. We go on to show how this so-called social summarization technique can generate summaries that are significantly better adapted to searcher preferences and describe a novel personalized search interface that combines result recommendation with social summarization.  相似文献   

7.
A well-known challenge for multi-document summarization (MDS) is that a single best or “gold standard” summary does not exist, i.e. it is often difficult to secure a consensus among reference summaries written by different authors. It therefore motivates us to study what the “important information” is in multiple input documents that will guide different authors in writing a summary. In this paper, we propose the notions of macro- and micro-level information. Macro-level information refers to the salient topics shared among different input documents, while micro-level information consists of different sentences that act as elaborating or provide complementary details for those salient topics. Experimental studies were conducted to examine the influence of macro- and micro-level information on summarization and its evaluation. Results showed that human subjects highly relied on macro-level information when writing a summary. The length allowed for summaries is the leading factor that affects the summary agreement. Meanwhile, our summarization evaluation approach based on the proposed macro- and micro-structure information also suggested that micro-level information offered complementary details for macro-level information. We believe that both levels of information form the “important information” which affects the modeling and evaluation of automatic summarization systems.  相似文献   

8.
Automatic text summarization has been an active field of research for many years. Several approaches have been proposed, ranging from simple position and word-frequency methods, to learning and graph based algorithms. The advent of human-generated knowledge bases like Wikipedia offer a further possibility in text summarization – they can be used to understand the input text in terms of salient concepts from the knowledge base. In this paper, we study a novel approach that leverages Wikipedia in conjunction with graph-based ranking. Our approach is to first construct a bipartite sentence–concept graph, and then rank the input sentences using iterative updates on this graph. We consider several models for the bipartite graph, and derive convergence properties under each model. Then, we take up personalized and query-focused summarization, where the sentence ranks additionally depend on user interests and queries, respectively. Finally, we present a Wikipedia-based multi-document summarization algorithm. An important feature of the proposed algorithms is that they enable real-time incremental summarization – users can first view an initial summary, and then request additional content if interested. We evaluate the performance of our proposed summarizer using the ROUGE metric, and the results show that leveraging Wikipedia can significantly improve summary quality. We also present results from a user study, which suggests that using incremental summarization can help in better understanding news articles.  相似文献   

9.
This paper presents a Foreign-Language Search Assistant that uses noun phrases as fundamental units for document translation and query formulation, translation and refinement. The system (a) supports the foreign-language document selection task providing a cross-language indicative summary based on noun phrase translations, and (b) supports query formulation and refinement using the information displayed in the cross-language document summaries. Our results challenge two implicit assumptions in most of cross-language Information Retrieval research: first, that once documents in the target language are found, Machine Translation is the optimal way of informing the user about their contents; and second, that in an interactive setting the optimal way of formulating and refining the query is helping the user to choose appropriate translations for the query terms.  相似文献   

10.
In recent years, there has been a rapid growth of user-generated data in collaborative tagging (a.k.a. folksonomy-based) systems due to the prevailing of Web 2.0 communities. To effectively assist users to find their desired resources, it is critical to understand user behaviors and preferences. Tag-based profile techniques, which model users and resources by a vector of relevant tags, are widely employed in folksonomy-based systems. This is mainly because that personalized search and recommendations can be facilitated by measuring relevance between user profiles and resource profiles. However, conventional measurements neglect the sentiment aspect of user-generated tags. In fact, tags can be very emotional and subjective, as users usually express their perceptions and feelings about the resources by tags. Therefore, it is necessary to take sentiment relevance into account into measurements. In this paper, we present a novel generic framework SenticRank to incorporate various sentiment information to various sentiment-based information for personalized search by user profiles and resource profiles. In this framework, content-based sentiment ranking and collaborative sentiment ranking methods are proposed to obtain sentiment-based personalized ranking. To the best of our knowledge, this is the first work of integrating sentiment information to address the problem of the personalized tag-based search in collaborative tagging systems. Moreover, we compare the proposed sentiment-based personalized search with baselines in the experiments, the results of which have verified the effectiveness of the proposed framework. In addition, we study the influences by popular sentiment dictionaries, and SenticNet is the most prominent knowledge base to boost the performance of personalized search in folksonomy.  相似文献   

11.
In the context of social media, users usually post relevant information corresponding to the contents of events mentioned in a Web document. This information posses two important values in that (i) it reflects the content of an event and (ii) it shares hidden topics with sentences in the main document. In this paper, we present a novel model to capture the nature of relationships between document sentences and post information (comments or tweets) in sharing hidden topics for summarization of Web documents by utilizing relevant post information. Unlike previous methods which are usually based on hand-crafted features, our approach ranks document sentences and user posts based on their importance to the topics. The sentence-user-post relation is formulated in a share topic matrix, which presents their mutual reinforcement support. Our proposed matrix co-factorization algorithm computes the score of each document sentence and user post and extracts the top ranked document sentences and comments (or tweets) as a summary. We apply the model to the task of summarization on three datasets in two languages, English and Vietnamese, of social context summarization and also on DUC 2004 (a standard corpus of the traditional summarization task). According to the experimental results, our model significantly outperforms the basic matrix factorization and achieves competitive ROUGE-scores with state-of-the-art methods.  相似文献   

12.
Satisfying information needs with multi-document summaries   总被引：2，自引：0，他引：2  
Generating summaries that meet the information needs of a user relies on (1) several forms of question decomposition; (2) different summarization approaches; and (3) textual inference for combining the summarization strategies. This novel framework for summarization has the advantage of producing highly responsive summaries, as indicated by the evaluation results.  相似文献   

13.
Centroid-based summarization of multiple documents   总被引：2，自引：0，他引：2  
We present a multi-document summarizer, MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We describe two new techniques, a centroid-based summarizer, and an evaluation scheme based on sentence utility and subsumption. We have applied this evaluation to both single and multiple document summaries. Finally, we describe two user studies that test our models of multi-document summarization.  相似文献   

14.
Increases in the amount of text resources available via the Internet has amplified the need for automated document summarizing tools. However, further efforts are needed in order to improve the quality of the existing summarization tools currently available. The current study proposes Karcı Summarization, a novel methodology for extractive, generic summarization of text documents. Karcı Entropy was used for the first time in a document summarization method within a unique approach. An important feature of the proposed system is that it does not require any kind of information source or training data. At the stage of presenting the input text, a tool for text processing was introduced; known as KUSH (named after its authors; Karcı, Uçkan, Seyyarer, and Hark), and is used to protect semantic consistency between sentences. The Karcı Entropy-based solution chooses the most effective, generic and most informational sentences within a paragraph or unit of text. Experimentation with the Karcı Summarization approach was tested using open-access document text (Document Understanding Conference; DUC-2002, DUC-2004) datasets. Performance achievement of the Karcı Summarization approach was calculated using metrics known as Recall-Oriented Understudy for Gisting Evaluation (ROUGE). The experimental results showed that the proposed summarizer outperformed all current state-of-the-art methods in terms of 200-word summaries in the metrics of ROUGE-1, ROUGE-2, ROUGE-L, and ROUGE-W-1.2. In addition, the proposed summarizer outperformed the nearest competitive summarizers by a factor of 6.4% for ROUGE-1 Recall on the DUC-2002 dataset. These results demonstrate that Karcı Summarization is a promising technique and it is therefore expected to attract interest from researchers in the field. Our approach was shown to have a high potential for adoptability. Moreover, the method was assessed as quite insensitive to disorderly and missing texts due to its KUSH text processing module.  相似文献   

15.
Information retrieval systems consist of many complicated components. Research and development of such systems is often hampered by the difficulty in evaluating how each particular component would behave across multiple systems. We present a novel integrated information retrieval system—the Query, Cluster, Summarize (QCS) system—which is portable, modular, and permits experimentation with different instantiations of each of the constituent text analysis components. Most importantly, the combination of the three types of methods in the QCS design improves retrievals by providing users more focused information organized by topic.We demonstrate the improved performance by a series of experiments using standard test sets from the Document Understanding Conferences (DUC) as measured by the best known automatic metric for summarization system evaluation, ROUGE. Although the DUC data and evaluations were originally designed to test multidocument summarization, we developed a framework to extend it to the task of evaluation for each of the three components: query, clustering, and summarization. Under this framework, we then demonstrate that the QCS system (end-to-end) achieves performance as good as or better than the best summarization engines.Given a query, QCS retrieves relevant documents, separates the retrieved documents into topic clusters, and creates a single summary for each cluster. In the current implementation, Latent Semantic Indexing is used for retrieval, generalized spherical k-means is used for the document clustering, and a method coupling sentence “trimming” and a hidden Markov model, followed by a pivoted QR decomposition, is used to create a single extract summary for each cluster. The user interface is designed to provide access to detailed information in a compact and useful format.Our system demonstrates the feasibility of assembling an effective IR system from existing software libraries, the usefulness of the modularity of the design, and the value of this particular combination of modules.  相似文献   

16.
Considerable evidence exists to show that the use of term relevance weights is beneficial in interactive information retrieval. Various term weighting systems are reviewed. An experiment is then described in which information retrieval users are asked to rank query terms in decreasing order of presumed importance prior to actual search and retrieval. The experimental design is examined, and various relevance ranking systems are evaluated, including fully automatic systems based on inverse document frequency parameters, human rankings performed by the user population, and combinations of the two.  相似文献   

17.
Text summarization is a process of generating a brief version of documents by preserving the fundamental information of documents as much as possible. Although most of the text summarization research has been focused on supervised learning solutions, there are a few datasets indeed generated for summarization tasks, and most of the existing summarization datasets do not have human-generated goal summaries which are vital for both summary generation and evaluation. Therefore, a new dataset was presented for abstractive and extractive summarization tasks in this study. This dataset contains academic publications, the abstracts written by the authors, and extracts in two sizes, which were generated by human readers in this research. Then, the resulting extracts were evaluated to ensure the validity of the human extract production process. Moreover, the extractive summarization problem was reinvestigated on the proposed summarization dataset. Here the main point taken into account was to analyze the feature vector to generate more informative summaries. To that end, a comprehensive syntactic feature space was generated for the proposed dataset, and the impact of these features on the informativeness of the resulting summary was investigated. Besides, the summarization capability of semantic features was experienced by using GloVe and word2vec embeddings. Finally, the use of ensembled feature space, which corresponds to the joint use of syntactic and semantic features, was proposed on a long short-term memory-based neural network model. ROUGE metrics evaluated the model summaries, and the results of these evaluations showed that the use of the proposed ensemble feature space remarkably improved the single-use of syntactic or semantic features. Additionally, the resulting summaries of the proposed approach on ensembled features prominently outperformed or provided comparable performance than summaries obtained by state-of-the-art models for extractive summarization.  相似文献   

18.
Access to information via handheld devices supports decision making away from one’s computer. However, limitations include small screens and constrained wireless bandwidth. We present a summarization method that transforms online content for delivery to small devices. Unlike previous algorithms, ours assumes nothing about document formatting, and induces a hierarchical structure based on the relative importance of sentences within the document. As compared to delivering full documents, the method reduces the bytes transferred by half. An experiment also demonstrates that when given hierarchical summaries, users are no less accurate in answering questions about the documents.  相似文献   

19.
Opinion summarization can facilitate user’s decision-making by mining the salient review information. However, due to the lack of sufficient annotated data, most of the early works are based on extractive methods, which restricts the performance of opinion summarization. In this work, we aim to improve the informativeness of opinion summarization to provide better guidance to users. We consider the setting with only reviews without corresponding summaries, and propose an aspect-augmented model for unsupervised abstractive opinion summarization, denoted as AsU-OSum. We first employ an aspect-based sentiment analysis system to extract opinion phrases from reviews. Then, we construct a heterogeneous graph consisting of reviews and opinion clusters as nodes, which is used to enhance the Transformer-based encoder–decoder framework. Furthermore, we design a novel cascaded attention mechanism to prompt the decoder to pay more attention to the aspects that are more likely to appear in summary. During training, we introduce a sentiment accuracy reward that further enhances the learning ability of our model. We conduct comprehensive experiments on the Yelp, Amazon, and Rotten Tomatoes datasets. Automatic evaluation results show that our model is competitive and performs better than the state-of-the-art (SOTA) models on some ROUGE metrics. Human evaluation results further verify that our model can generate more informative summaries and reduce redundancy.  相似文献   

20.
Document concept lattice for text understanding and summarization   总被引：4，自引：0，他引：4  
We argue that the quality of a summary can be evaluated based on how many concepts in the original document(s) that can be preserved after summarization. Here, a concept refers to an abstract or concrete entity or its action often expressed by diverse terms in text. Summary generation can thus be considered as an optimization problem of selecting a set of sentences with minimal answer loss. In this paper, we propose a document concept lattice that indexes the hierarchy of local topics tied to a set of frequent concepts and the corresponding sentences containing these topics. The local topics will specify the promising sub-spaces related to the selected concepts and sentences. Based on this lattice, the summary is an optimized selection of a set of distinct and salient local topics that lead to maximal coverage of concepts with the given number of sentences. Our summarizer based on the concept lattice has demonstrated competitive performance in Document Understanding Conference 2005 and 2006 evaluations as well as follow-on tests.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号