Estimating Risk of Picking a Sentence for Document Summarization

Kumar, Chandan; Pingali, Prasad; Varma, Vasudeva

doi:10.1007/978-3-642-00382-0_46

Cited by 6 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graphs have been used to determine salient parts of text [Mihalcea, 2004, Erkan and Radev, 2004a, Erkan and Radev, 2004b or query related sentences in close relation to the summarization process. Lexical relationships [Mohamed and Rajasekaran, 2006] or rhetorical structure [Marcu, 2000] and even non-apparent information [Lamkhede, 2005] have been represented by graphs. Graphs have also been used to detect differences and similarities between source texts [Mani and Bloedorn, 1997] and inter-document relations [Witte et al, 2006], as well as relations of various granularity from cross-word to cross-document as described in Cross-Document Structure Theory .…”

Section: Graph-based Methods and Graph Matchingmentioning

confidence: 99%

See 1 more Smart Citation

MUDOS-NG: Multi-document Summaries Using N-gram Graphs (Tech Report)

Giannakopoulos,

Vouros,

Karkaletsis

2010

Preprint

View full text Add to dashboard Cite

This report describes the MUDOS-NG summarization system, which applies a set of language-independent and generic methods for generating extractive summaries. The proposed methods are mostly combinations of simple operators on a generic character n-gram graph representation of texts. This work defines the set of used operators upon n-gram graphs and proposes using these operators within the multi-document summarization process in such subtasks as document analysis, salient sentence selection, query expansion and redundancy control. Furthermore, a novel chunking methodology is used, together with a novel way to assign concepts to sentences for query expansion. The experimental results of the summarization system, performed upon widely used corpora from the Document Understanding and the Text Analysis Conferences, are promising and provide evidence for the potential of the generic methods introduced. This work aims to designate core methods exploiting the n-gram graph representation, providing the basis for more advanced summarization systems.

show abstract

Section: Graph-based Methods and Graph Matchingmentioning

confidence: 99%

“…The notion of Bayesian expected risk (or loss) is applied in the summarization domain by [Kumar et al, 2009], where the selection of sentences is viewed as a decision process, where the selection of each sentence is considered a decision and the system has to select the sentences that minimize the risk.…”

Section: Salience Detectionmentioning

confidence: 99%

MUDOS-NG: Multi-document Summaries Using N-gram Graphs (Tech Report)

Giannakopoulos,

Vouros,

Karkaletsis

2010

Preprint

View full text Add to dashboard Cite

show abstract

“…Each possible action should be evaluated based on all available parameters (discussed above) associated with it and the best possible actions would be ranked higher. There can be many possible criteria to choose a particular action, e.g., the risk/error minimization principle has been quite successful for information science studies Figure 2: probable ranking framework due to its strong information theory and probabilistic background Kumar et al (2009); Lafferty and Zhai (2001); Lavrenko and Croft (2001).…”

Section: Formalization Of Relevance Parameters For Rankingmentioning

confidence: 99%

Relevance and Ranking in Geographic Information Retrieval

Kumar

2011

Electronic Workshops in Computing

View full text Add to dashboard Cite

Geographic Information Retrieval (GIR) is a specialized branch of traditional Information Retrieval (IR), which deals with the information related to geographic locations. One of the main challenges of GIR is to quantify the spatial relevance of documents and generate a pertinent ranking of the results according to the spatial information needs of user. Most of the current methods judge the relevance of documents just based on textual and spatial similarity with the query, and ranked the results with a linear combination of these similarity measures. We consider relevance ranking as a much more dynamic problem stemming from real world application such as location based mobile services, where user not only seek information but there is a decision making involved with the search i.e. to visit the location. In this paper we discuss current ranking phenomenon in geographic information retrieval, present different relevant parameters based on our initial study, and argue for the need of a formal relevance framework and ranking mechanism for geographical information retrieval. We approach GIR ranking as a spatial decision problem to support user's activity, and propose the idea to explore decision-theoretic framework and probabilistic representation for geo relevance formalization.

show abstract

“…However, doing so may result in selection of redundant sentences. To help mitigate this problem, one may only select sentences that have less than a certain degree of overlap with every sentence in the summary set (Kumar et al, 2009). More sophisticated approaches, such as the MMR algorithm, formulate the sentence selection problem as a search problem that seeks to maximize an objective function which gives credit for the relevance score, and penalizes for overlap (Carbonell and Goldstein, 1998).…”

Section: Selecting Multiple Sentencesmentioning

confidence: 99%

“…Experiments did not show many differences between these methods, and for our evaluation, we use the aforementioned approach used in (Kumar et al, 2009).…”

Section: Selecting Multiple Sentencesmentioning

confidence: 99%

An Approach for Combining Semantic Information and Proximity Information for Text Summarization

Jeong

Yun

2011

Proceedings of the International Conference on Knowledge Discovery and Information Retrieval

View full text Add to dashboard Cite

This paper develops and evaluates an approach for combining semantic information with proximity information for text summarization. The approach is based on the proximity language model, which incorporates proximity information into the unigram language model. This paper novelly expands the proximity language model to also incorporate semantic information using latent semantic analysis (LSA). We argue that this approach achieves a good balance between syntactic and semantic information. We evaluate the approach using ROUGE scores on the Text Analysis Conference (TAC) 2009 Summarization task, and find that incorporating LSA into PLM gives improvements over the baseline models. 3 PROXIMITY LANGUAGE MODEL Proximity language model (PLM) forms the heart of our ranking function, and is based on the unigram language model (Zhao and Yun, 2009).

show abstract

Estimating Risk of Picking a Sentence for Document Summarization

Cited by 6 publications

References 13 publications

MUDOS-NG: Multi-document Summaries Using N-gram Graphs (Tech Report)

MUDOS-NG: Multi-document Summaries Using N-gram Graphs (Tech Report)

Relevance and Ranking in Geographic Information Retrieval

An Approach for Combining Semantic Information and Proximity Information for Text Summarization

Contact Info

Product

Resources

About