Semantic Search on Text and Knowledge Bases

Bast, Hannah; Buchhold, Björn; Haußmann, Elmar

doi:10.1561/1500000032

Cited by 124 publications

(92 citation statements)

References 134 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Semantic measurement of similarity ensures that not only the matching word based jobs are retrieved rather based on qualification, experience and searching prospective jobs are shown. H. Bast [16] has proposed mining-based methodology in the text database to form the knowledge graph and sort out the similarity.…”

Section: Related Workmentioning

confidence: 99%

Enhancing the Performance of Semantic Search in Bengali using Neural Net and other Classification Techniques

Das¹,

Saha²

2020

IJEAT

View full text Add to dashboard Cite

To know the information from the internet searching is one of the most important part for any user. In case of ‘Syntactic Search’ keyword based matching technique is used. Search accuracy is improved applying the filter like location, preference, user-history etc. However, it can happen that the user query or question and the best available answer or result in the internet domain has no terms in common or ignorable number of terms is common. In such case syntactic search cannot give the desired output. The role of ‘Semantic Search’ becomes prevalent in this scenario. The execution of semantic search faces challenge due to unavailability of resources like WordNet, Ontology, Annotation etc. An end to end algorithm is described to improve the accuracy of the semantic search in this work. Four classification techniques are used. They are ANN, Decision Tree, SVM and Naïve Bayes. Dataset is provided from the TDIL project of the Ministry of Electronics and IT, Govt. of India. The repository contains 86 categories of text having more than a million sentences. After getting the impressive result for the Bengali language test run was done for other Indian languages and a very good result is achieved. This research is extremely useful for the automatic question answering system, semantic similarity analysis, e-governance and m- governance.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing the Performance of Semantic Search in Bengali using Neural Net and other Classification Techniques

Das¹,

Saha²

2020

IJEAT

View full text Add to dashboard Cite

show abstract

“…Over the last five years, knowledge harvesting has been adopted at big industrial stakeholders, and large KB's have become a key asset in a variety of commercial applications, including semantic search (see, e.g., [4]), analytics (e.g., aggregating by entities), recommendations and data integration (i.e., to combine heterogeneous datasets in and across enterprises). Examples are the Google Knowledge Graph (with Freebase as a catalyst), the use of KB's in IBM Watson, Amazon's Evi, the Baidu Knowledge Graph, Facebook's Graph Search, Microsoft Satori, Wolfram Alpha as well as domain-specific knowledge bases in business, finance, life sciences, and more (e.g., at Bloomberg, Mayo Clinic, Siemens, Wal-mart, etc.).…”

Section: Introductionmentioning

confidence: 99%

Knowledge Harvesting: Achievements and Challenges

Weikum

Hoffart²,

Suchanek

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Semantic search is a search that is based on the meaning rather than the syntax of the query. Semantic Search has been largely studied during the last few years, [1] provide a recent survey of this research. In addition to research solution many Semantic Search Engine have recently emerged, for example: Hakia, Kosmix, Swoogle, Cognition, Lexxe, Kngine, Powerset, DuckDuckGo, Sensebot [2][3] [4].…”

Section: Introductionmentioning

confidence: 99%

“…In addition to research solution many Semantic Search Engine have recently emerged, for example: Hakia, Kosmix, Swoogle, Cognition, Lexxe, Kngine, Powerset, DuckDuckGo, Sensebot [2][3] [4]. Google search engine has also been improving its semantic search abilities as it answers an increasing fraction of natural language queries [1].…”

Section: Introductionmentioning

confidence: 99%

“…According to [1], all Semantic Search techniques introduced so far merely simulate an understanding of the meaning of the search rather than providing real understanding of the search. [5] have presented four common issues that face intelligent semantic search engines, namely: (1) low precision and high recall, (2) identifying intention of the user, (3) extrapolation of users' search patterns, and (4) handling inaccurate queries.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Searchsense: A Semantic Meta Search Engine

Elsayed

2018

IJICIS

View full text Add to dashboard Cite

Despite the recent advancements in information retrieval research and in online search engines, satisfying the needs of search engines users remains largely challenging. This is due to many reasons including the size and richness of information available over the internet and the semantic gap between the intention of search engine user and how search engines understand that intention.This article highlights the main reasons for ineffective web searches and sheds the lights on the status of ongoing research stream, the SearchSense project, which focuses on improving the effectiveness of search engines in satisfying users' needs. The research has been carried out through multiple projects that were implemented over several years with main overall focus on designing an effective semantic search engine. SearchSense employs the semantic technology to bridge the gap between search engines and their users and to provide a better presentation of web search results. SearchSense could be used as a Meta Semantic Search Engine on top of regular search engine or could easily be incorporated in any information retrieval system.The article describes the overall framework of the solution and outlines its main components. Details on the technicalities of the solution components are presented in relevant articles. The article also provided a summary of the results of the experiments that have been conducted to test the effectiveness of the solution.

show abstract

Semantic Search on Text and Knowledge Bases

Cited by 124 publications

References 134 publications

Enhancing the Performance of Semantic Search in Bengali using Neural Net and other Classification Techniques

Enhancing the Performance of Semantic Search in Bengali using Neural Net and other Classification Techniques

Knowledge Harvesting: Achievements and Challenges

Searchsense: A Semantic Meta Search Engine

Contact Info

Product

Resources

About