Tag-oriented document summarization

Zhu, Jun‐Yan; Wang, Can; He, Xiaofei; Bu, Jiajun; Chen, Chun; Shang, Shujie; Qu, Mingcheng; Lü, Gang

doi:10.1145/1526709.1526925

Cited by 26 publications

(16 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sentencebased summarization focuses on partitioning documents in sentences and generating a summary that consists of the subset of most informative sentences (e.g., [11,29,47]). In contrast, keyword-based approaches focus on detecting salient document keywords using, for instance, graph-based indexing [28,51,52] or latent semantic analysis [16]. Since sentence-based approaches commonly generate humanly readable summaries without the need for advanced postprocessing steps, our summarizer relies on a sentencebased approach.…”

Section: Related Workmentioning

confidence: 99%

“…For example, clustering-based approaches (e.g., [47,48]) adopt clustering algorithms to group document sentences into homogeneous clusters and then select the most authoritative representatives within each group. In contrast, graph-based approaches (e.g., [36,51,52]) first generate a graph-based model in which the similarity relationships between pairs of sentences are represented. Next, they exploit popular indexing strategies (e.g., PageRank [9]) to identify the most salient sentences (i.e., the most authoritative graph nodes).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-document summarization based on the Yago ontology

Baralis

Cagliero

Jabeen

et al. 2013

Expert Systems with Applications

View full text Add to dashboard Cite

Sentence-based multi-document summarization is the task of generating a succinct summary of a document collection, which consists of the most salient document sentences. In recent years, the increasing availability of semanticsbased models (e.g., ontologies and taxonomies) has prompted researchers to investigate their usefulness for improving summarizer performance. However, semantics-based document analysis is often applied as a preprocessing step, rather than integrating the discovered knowledge into the summarization process.that relies on an ontology-based evaluation and selection of the document sentences. To capture the actual meaning and context of the document sentences and generate sound document summaries, an established entity recognition and disambiguation step based on the Yago ontology is integrated into the summarization process.The experimental results, which were achieved on the DUC'04 benchmark collections, demonstrate the effectiveness of the proposed approach compared to a large number of competitors as well as the qualitative soundness of the generated summaries.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-document summarization based on the Yago ontology

Baralis

Cagliero

Jabeen

et al. 2013

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…Hu et al [2008] also used user comments to assist summarization and they experimented with various methods for weighting the comments and creating the summary. Zhu et al [2009] used information from user tags to assist summarization, and to that purpose they developed a HITS-type of ranking method. Finally, Boydell and Smyth [2010] use tag information from delicious to assist to the extraction of snippets from Web documents.…”

Section: Web Page Summarizationmentioning

confidence: 99%

Web Page Summarization for Just-in-Time Contextual Advertising

Anagnostopoulos

Bröder

Gabrilovich

et al. 2011

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Contextual advertising is a type of Web advertising, which, given the URL of a Web page, aims to embed into the page the most relevant textual ads available. For static pages that are displayed repeatedly, the matching of ads can be based on prior analysis of their entire content; however, often ads need to be matched to new or dynamically created pages that cannot be processed ahead of time. Analyzing the entire content of such pages on-the-fly entails prohibitive communication and latency costs. To solve the three-horned dilemma of either low relevance or high latency or high load, we propose to use text summarization techniques paired with external knowledge (exogenous to the page) to craft short page summaries in real time. Empirical evaluation proves that matching ads on the basis of such summaries does not sacrifice relevance, and is competitive with matching based on the entire page content. Specifically, we found that analyzing a carefully selected 6% fraction of the page text can sacrifice only 1%-3% in ad relevance. Furthermore, our summaries are fully compatible with the standard JavaScript mechanisms used for ad placement: they can be produced at ad-display time by simple additions to the usual script, and they only add 500-600 bytes to the usual request. We also compared our summarization approach, which is based on structural properties of the HTML content of the page, with a more principled one based on one of the standard text summarization tools (MEAD), and found their performance to be comparable

show abstract

“…Our problem of finding discriminative items between two streams can provide solutions to many Web mining applications such as tag suggestions [22,28,42,53] summarizing web documents [40,59], emails [10], or Web search results [32], search engine query analysis [56], social network analysis [49,54], and so on. An essential issue inherent in those applications is to find discriminative tags or keywords that can distinguish the targeting object from many others.…”

Section: Related Workmentioning

confidence: 99%