Information retrieval as statistical translation

Berger, Adam; Lafferty, John

doi:10.1145/312624.312681

Cited by 386 publications

(165 citation statements)

References 9 publications

Supporting

Mentioning

165

Contrasting

Order By: Relevance

“…P (e | q, E) (1) [11]. As the above notation suggests, numerous approaches to this problem involve probability and statistics, while others propose vector based models to enhance the retrieval.…”

Section: Our Methodsmentioning

confidence: 99%

Email classification: Solution with back propagation technique

Ayodele

Zhou

Khusainov

2009

2009 International Conference for Internet Technology and Secured Transactions, (ICITST)

View full text Add to dashboard Cite

To acquire knowledge by learning automatically from the data, through a process of inference, model fitting, or learning from example is one of the rare field of email management. And when an artificial system can perform "intelligent", tasks similar to those performed by the human brain and such is implemented in email classification, such a system will be is extremely intelligent. Using neural network for email content classification with back propagation is where our technique becomes distinct and effective. This paper proposes a new email classification model using a teaching process of multi-layer neural network to implement back propagation algorithm. Our contributions are: the use of empirical analysis to select an optimum, novel collection of features of a user's email message content that enables the rapid detection of most important words, phrases in emails and a demonstration of the effectiveness of two equal sets of emails (training and testing data).

show abstract

Section: Our Methodsmentioning

confidence: 99%

Email classification: Solution with back propagation technique

Ayodele

Zhou

Khusainov

2009

2009 International Conference for Internet Technology and Secured Transactions, (ICITST)

View full text Add to dashboard Cite

show abstract

“…We leverage Query likelihood retrieval model [16] to analyze relevance, which is proved effective in [11]. We model the relevance of a product with conditional probability p(t, | ), which can be interpreted as the posterior probability that a new or unpopular product is relevant to a review sentence t of other product .…”

Section: Modeling Relevancementioning

confidence: 99%

MSRM: A Novel Model to Retrieve Meaningful Opinion Sentences for New Products

Du¹,

Xu²,

Huang³

2018

dtcse

View full text Add to dashboard Cite

Abstract. Online reviews are more and more important for potential consumers to make purchase decisions. The referred information of the new products or unpopular products that have no reviews or very few reviews is limited and this situation makes it difficult for consumers to obtain enough information to understand these products. Indeed, this is a new issue recently that needs to be addressed. In this paper, we study the problem of automatically retrieving meaningful opinion sentences for a new product or unpopular product from reviews of other similar products. The retrieved meaningful opinion sentences should possess three properties: helpfulness, relevance and coverage. We propose a meaningful sentences retrieval model (MSRM), which is centered on these three properties to extract meaningful opinion sentences for a new product or unpopular product. We employ product specifications to estimate similarity between products, and model helpfulness, relevance and coverage properties respectively, finally incorporate these three properties into MSRM to mine meaningful sentences from reviews of similar products. Through a series of experiments on real data sets, experiment results show MSRM achieves much better performance.

show abstract

“…Translation models, in a monolingual setting, have been used for document retrieval [10], question answering [11], and detecting text reuse [12]. The goal is to measure the likelihood that some candidate document or sentence is a translation (or transformation) of the query.…”

Section: Related Workmentioning

confidence: 99%

A new approach to short web document creation based on textual and visual information

Zachariášová

Kamencay

Hudec

et al. 2013

2013 36th International Conference on Telecommunications and Signal Processing (TSP)

View full text Add to dashboard Cite

This paper deals with research in area of automatic semantic inclusion of textual and non-textual information of Web documents. The main idea is to create a robust method for extraction of images and textual segments to obtain short web document. Thus, developed method consist of two data types extractions, where both, image and text data extraction are using Document Object Model (DOM) tree. Extracted objects are saved in separated databases followed by the images analysis that defines and describes image object from semantic point of view. Moreover, the semantic descriptions of all modal objects are utilized to short web document creation. We implement our novel method using the Scale Invariant Feature Transform (SIFT) descriptor within a Support Vector Machine (SVM) classifier. Further, in order to obtain a semantic description of objects in static image, the Support Vector Machine (SVM) classification were applied. Finally, semantic inclusion textual and visual information was realized. The developed method has been tested on real and off-line web documents.

show abstract

Information retrieval as statistical translation

Cited by 386 publications

References 9 publications

Email classification: Solution with back propagation technique

Email classification: Solution with back propagation technique

MSRM: A Novel Model to Retrieve Meaningful Opinion Sentences for New Products

A new approach to short web document creation based on textual and visual information

Contact Info

Product

Resources

About