Disambiguation of Keywords in Microposts
Sathiyasri and Akilandeswari,Sona College Of Technology,India
ABSTRACT
Small and noisy text snippets are created by users of social networks such as Twitter and Facebook. The full interpretation of the microposts by machines imposes tremendous challenges, since they strongly rely on context. Classification systems to detect the keyword that unambiguously refers to a single dominant concept, even when it is taken out of context. For example, in the context of the task, apple would be classified as ambiguous whereas Microsoft would not. The contribution of work is to formalize the concept of disambiguating the texts based on conceptual ontology.
Semantic Tagging for Documents using 'Short Text' Information
AyushSinghal and Jaideep Srivastava,University of Minnesota,United States
ABSTRACT
Tagging documents with relevant and comprehensive keywords offer invaluable assistance to the readers to quickly overview any document. With the ever increasing volume and variety of the documents published on the internet, the interest in developing newer and successful techniques for annotating (tagging) documents is also increasing. However, an interesting challenge in document tagging occurs when the full content of the document is not readily accessible. In such a scenario, techniques which use “short text”, e.g., a document title, a news article headline, to annotate the entire article are particularly useful. In this paper, we pro- pose a novel approach to automatically tag documents with relevant tags or key-phrases using only “short text” information from the documents. We employ crowd-sourced knowledge from Wikipedia, Dbpedia, Freebase, Yago and similar open source knowledge bases to generate semantically relevant tags for the document. Using the intelligence from the open web, we prune out tags that create ambiguity in or “topic drift” from the main topic of our query document. We have used real world dataset from a corpus of research articles to annotate 50 research articles. As a baseline, we used the full text information from the document to generate tags. The proposed and the baseline approach were compared using the author assigned keywords for the documents as the ground truth information. We found that the tags generated using proposed approach are better than using the baseline in terms of overlap with the ground truth tags measured via Jaccard index (0.058 vs. 0.044). In terms of computational efficiency, the proposed approach is at least 3 times faster than the baseline approach. Finally, we qualitatively analyse the quality of the predicted tags for a few samples in the test corpus. The evaluation shows the effectiveness of the proposed approach both in terms of quality of tags generated and the computational time.
Better Control Authority Flow Using Topicality with Proximity Search
Dinesh Reddy Vemula,Balaji Institute of technology & science,India
ABSTRACT
The authority of web pages can be better estimated by controlling the authority flows among pages. Due to the complexity of calculating the authority flow, current systems only use pre computed authority flows in runtime. This limitation prohibits authority flow to be used more effectively as ranking factor. Proximity search have been used extensively in measuring the association between entities in data graphs. A key advantage of proximity search is the existence of efficient execution algorithms. However, it is desirable to be able to onthe-fly compute the authority flow at query time with this. Web pages are often recognized by others through contexts. In this work, we use proximity by examining the topicality relationship between associated pages to determine the authority distribution.In addition , we consider influence of authority propagation from diverse types of neighbours, since web pages, like people,are influenced by diverse types of neighbours within the same network. We propose a probabilistic method to model authority flows from different sources of neighbour pages. Experiments on the 2003 and 2004 TREC Web tracks demonstrate that this approach outperforms other competitive topical ranking models and produces more than 10% improvement over Page Rank on the quality of top ten search results. When increasing the types of incorporated neighbour sources, the performance shows stable improvements.
Mobile Cloud Using Android
Swanand Wakhade and Veena Gulhane,GHRCE,India
ABSTRACT
The number of Smartphone users and mobile application are increase rapidly. Though smart phones are expected to have PC-like functionality, hardware resources such as CPUs and batteries are limited. To solve this resource problem, many researchers have give architectures to use server resources in the cloud for mobile devices. We give a conceptual architecture of Android application on cloud server network. Though Android is mainly designed for physical Smartphone, Android’s two other features are very useful to construct a server platform. Android is open-source product and run on an x86 CPU. We show three types of multi-tenant architecture for an Android server platform and
discuss the direction to take to it reality.
Intrusion Detection For Mobile Ad-Hoc Network
Deepika Dua and Atul Mishra,Y.M.C.A. University of Science and Technology,India
ABSTRACT
Mobile ad-hoc networks(MANET) are the networks which uses the wireless medium for
communication ,every node is free to either join or leave the network and the nodes in such a network have no fixed topology, the topology changes with time as the nodes move from one place to another. So in such a network, security can be easily compromised as the attacker can introduce its malicious node in the network and can degrade the network performance. As a result there is a need of a intrusion detection system. This paper describes a scheme that will detect the intrusion in the network and will help improve the network performance in the presence of malicious node
Survey On Tools And Techniques For Ontology Interoperability In Semantic Web
Lakshmi Tulasi 1 ,Srinivasa Rao Meda 2,1 QIS college of engineering & technology ,2 JNTUH,India
ABSTRACT
Ontology is a shared conceptualization of knowledge representation of particular domain. These are used
for the enhancement of semantic information explicitly. It is considered as a key element in semantic web
development. Creation of global web data sources is impossible because of the dynamic nature of the
web. Different domain experts and ontology engineers create different ontologies for the same or similar
domain depending on their data modelling requirements. These cause ontology heterogeneity and
inconsistency problems. For more better and precise results ontology mapping is the solution. three
important operations on ontologies are proposed. Papers on ontology matching report the results on
different frameworks and this makes their comparison almost impossible. Therefore, the main focus of
this paper will be on providing some basics of ontology matching and briefly introducing its different
approaches. The aim of this paper is to give readers an idea about ontology alignment, ontology
mapping, ontology merging and its related techniques and tools.
PASSWORD: Storage, workflows and strength
Kriti,Adobe Systems,India
ABSTRACT
After so many years from the advent of passwords, we are still using text passwords as the primary method of authentication in one or the other way. Although there are a number of issues with the traditional password usage, no new technique has yet offered all the benefits of text passwords while at the same time also solving its shortcomings. Hence, we have taken up the text passwords and tried to analyze all the major areas pertaining to passwords that are most often exploited to gain hold of the secret information. In this paper we have attempted to analyze these areas from the authority’s perspective and latest technologies to find a common recommendation that can be followed. The three key areas that have been discussed are password storage, workflows and password strength
Social Business Transformation: A Paradigm shift towards System of Engagement Model
Jitendra Maan,Tata Consultancy Services Limited,India
ABSTRACT
Today.organization are morphing from customer-product hierarchies to intelligent engagement-centric platforms and networks where social business is evolving from a pure consumer phenomenon to a great systems of engagement which creates layer with all systems of references to establish an effective way to collaborate and communicate across the ecosystem.
The paper throws some lights on pervasive social layer that not only enables collaboration among stakeholders of each systems of record but the entire focus moves towards the systems of engagement architecture to establish an effective way to focus on systems of record integration, context awareness and gamification mechanics required for each moment of engagement and collaboration. To truly capitalize on such transformation, the paper talks about the building blocks of social business transformation program that capture the value of social technologies. It also outlines the various levers to transform customer experience by understanding the customer behavior which play a catalyst role in the co-creation of business value
