A Vector Space Model Approach for Searching and Matching Product E-Catalogues

Mehrbod, Ahmad; Zutshi, Aneesh; Grilo, António

doi:10.1007/978-3-642-55122-2_71

Cited by 10 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process assures that it derives the relationship between a word and the sentence through the meanings. Vector Space Models [5] are also being used in segmentation and every word is mapped in a vector that contains other words with a score that represents the connection between that word and the others.…”

Section: Litreture Reviewmentioning

confidence: 99%

Automated Classroom Lecture Note Generation Using Natural Language Processing and Image Processing Techniques

T.C.¹

2019

IJATCSE

View full text Add to dashboard Cite

Teachers use different teaching methods to deliver the course content to the learners. Smart learning environments helps to reform of the ways of teaching and learning through advancing current methods. These environments help learners to enhance their knowledge and skills by engaging in different learning activities. These different methods can be use of power point, white board drawings, and online learning platforms, audio and video inputs. Teacher's main aim is to maximize the learner engagement in developing knowledge and skills. The teachers' expectation is that the learner's to gather knowledge though the variety of lesson materials. This paper describes a research approach on how the learning materials, smart white board input and the lectures' voice input can be combined in generation of compiled lecture note. In developing the solution it has used the voice input, white board diagrams and other earning materials used in the classroom, materials given in the Learning Management System and any internet materials. The study has adapted Natural Language Processing and Image Processing techniques. Main components of the research were text segmentation, text summarization, topic modeling, and diagram recognition. Outcome of the research can be used by the teachers and learners in day today work.

show abstract

Section: Litreture Reviewmentioning

confidence: 99%

Automated Classroom Lecture Note Generation Using Natural Language Processing and Image Processing Techniques

T.C.¹

2019

IJATCSE

View full text Add to dashboard Cite

show abstract

“…The biggest disadvantage of this is that the users have to subscribe in all the platforms to be able to get access to various opportunities originating from different platforms and submit proposals for the opportunities. While using standard formats helps to use the same information in different documents in the process flow and decrease the efforts needed to correct errors and fix problems by automating e-procurement process, standards do not provide sufficient coverage for all steps of procurement (Mehrbod et al, 2014a).…”

Section: Matching Problemmentioning

confidence: 99%

“…In a previous work (Mehrbod et al, 2014a(Mehrbod et al, , 2014b(Mehrbod et al, , 2015 in a G2B2B procurement platform Called Vortal, we developed an e-catalogue matching engine that helps the buyers to find suitable suppliers on the platform based on the similarity between suppliers' product e-catalogues to the buyers' product requests. The heterogeneity of the underlying product catalogues was the main reason to use the concept-based VSM approach for developing a practical product matching engine.…”

Section: Proposed Solutionmentioning

confidence: 99%

“…the search service exploits the data and the structures of B2B documents in the matching process but is not independent of any pre-specified structure and can tolerate lack of such information using basic functionalities of VSM. For more details about the e-catalogue matching mechanism and used algorithms please refer to (Mehrbod et al, 2015(Mehrbod et al, , 2014b(Mehrbod et al, and 2014a.…”

Section: Proposed Solutionmentioning

confidence: 99%

See 1 more Smart Citation

Application of a semantic product matching mechanism in open tendering e-marketplaces

Mehrbod¹,

Zutshi²,

Grilo³

et al. 2018

JOPP

Self Cite

View full text Add to dashboard Cite

Purpose Searching the tender notices that publish every day in open tendering websites is a common way for finding business opportunity in public procurement. The heterogeneity of tender notices from various tendering marketplaces is a challenge for exploiting semantic technologies in the tender search. Design/methodology/approach Most of the semantic matching approaches require the data to be structured and integrated according to a data model. But the integration process can be expensive and time-consuming especially for multi-source data integration. Findings In this paper, a product search mechanism that had been developed in an e-procurement platform for matching product e-catalogues is applied to the tender search problem. The search performance has been compared using two procurement vocabularies on searching tender notices from two major tender resources. Originality/value The test results show that the matching mechanism is able to find tender notices from heterogeneous resources and different classification systems without transforming the tenders to a uniform data model.

show abstract

“…Grouping out an extensive arrangement of records into various comparative groups [17]. Along these lines, the records in a similar bunch are more like each other than to records in another group.…”

Section: *Author For Correspondencementioning

confidence: 99%

A survey and analysis based on topic based classification

Sikarwar¹,

Patidar²,

Kushwah³

2018

IJATEE

View full text Add to dashboard Cite

In this paper a survey and analysis based on topic based data classification has been presented. It includes the topic based data orientation, data categorization, document clustering, etc. This study provides the analytical way to analyze the methods previously published and provide explorative way of the approaches presented. It also provides the discussion based on the attributes and property used and explored. This study provides the discussion of different partitioning algorithm, different grouping methods and classification approaches.Based on the study, future enhancements have been suggested.

show abstract

A Vector Space Model Approach for Searching and Matching Product E-Catalogues

Cited by 10 publications

References 16 publications

Automated Classroom Lecture Note Generation Using Natural Language Processing and Image Processing Techniques

Automated Classroom Lecture Note Generation Using Natural Language Processing and Image Processing Techniques

Application of a semantic product matching mechanism in open tendering e-marketplaces

A survey and analysis based on topic based classification

Contact Info

Product

Resources

About