My decision to pursue a PhD is derived from my passion for science and engineering paired with my abilities in the field of machine learning and applied statistics. I consider myself fortunate to be part of the Department of Computer Science, University of Florida for my master studies. More importantly, I am glad to have two excellent professors in this field as advisors, Dr. Pader and Dr. Jilson, who are guiding me throughout my graduate studies. They assisted me to decide and pursue the courses and topics that interested me. During my first semester, I took the course Mathematical methods for Intelligent Systems that gave me a strong base for applied mathematics in the field of intelligent systems. Similarly, the research course …show more content…
Wilson in which I analyzed machine-learning techniques that could be used in a realm-based Question Answering system. My master’s thesis is an extension to this study, for which, I am working with “Morpheus” team at Database Research Center in our department. Our team is building a question answering system that uses deep web sources by exploiting information from Wikipedia and WordNet along with sample query answering strategies provided by users. The motivation behind this research work is as follows. If we search for an answer to a question in a typical search engines such as Google, Bing, or Yahoo, it usually gives us relevant pages based on the key words in the query. We may need to follow several links or pages to reach a document providing a relevant answer. If we can store such search pathways to an answer for a given user query and reuse it for future searches it may speed up this process. Our question answering system motivated by reuse of prior web search pathways to yield an answer a user query. We represent queries and search pathways in a semi-structured format that contains query terms and referenced classes within a realm based ontology. First part of my research is to build a system that can automatically tag the terms in a user query to relevant classes from a domain-based ontology. The other part is to rank the prior searches (contains user queries, assigned classes, and search pathways) stored in the database based on the
Through the methodology proposed, we aspire to achieve a more efficient technology for generating keywords and finding more accurate data from the search engine. By saving physical memory and storing only what is important rather than all the data from a random website. Also, due to this we may achieve faster response time. So, here we can conclude that the proposed system may be more better than the previous systems
Our reliance on the Internet is becoming too much for our own good. With no end in sight on advances to the Internet, there is no real way to know the impact the Internet is having, “Where does it end? Sergey Brin and Larry Page, the gifted young men who founded Google while pursuing doctoral degrees in computer science at Stanford, speak frequently of their desire to turn their search engine into an artificial intelligence, a HAL-like machine that might be
As society has progressed into the twenty-first century it is evident that humanity is becoming strongly reliant on technology, especially the internet in which people now use instantaneously on a daily basis, from diagnosing diseases to finding answers, information and gossip within moments of it occurring. Wikipedia is “a free, collaborative, multilingual internet encyclopedia. Wikipedia evolves without the supervision of a pre-selected expert
How easy is to implement the RTBF? A dreadful question with a not pragmatic answer; First, a search engine is like a library index with the assumption that the searching results will come up with no omission of information. Moreover, in analyzing the court ruling we can quickly agree in the inadequate and almost inexistent guidance from the European Union court to the data controllers such as Google, Microsoft Bing, and Yahoo in how to implement their ruling.
Contextual search launched and successful, overtaking Google on this future area of search engine technology.
The web has grown tremendously since that time, and now these methods are no longer viable. Instead of focusing on keywords, search engine algorithms attempt to “understand” your content. The latest news of Google’s new RankBrain algorithm is just one example of why the future of SEO will change Internet marketing.
The paper Semantic Web talks about how the machine can be more intelligent when accessing web data. It involves making a machine understand the semantics of the data present on the web and also making them understand the human perspective. The research first tries the basic requirement outlines for the semantic web. Like the creation of ontologies and different relationship using which a machine can learn the context. The paper then discusses the creation of agents which takes advantage of the semantic web technology and gives a more personalized output to the user. In the paper the author has taken few real life examples is setting the benchmark requirements of the semantic web.
G. Madhu, Dr. A. Govardhan, and Dr. TV Rajinikanth in their survey of intelligent semantic web search engines have addressed the two types of research problems in creating semantic search engine. The first problem of matching a query to the concerned documents with related information in an intelligent and meaningful way can be solved with semantic annotations to produce intelligent and meaningful information by using query interface mechanism and
In which rules are created from answers provided by users on questions about information usage and filtering behavior. Our system considers user’s profile (based on user’s weblog/navigation browsing history) and Domain Knowledge in order to perform personalized web search. Using Domain Knowledge, the system stores information about different domain/categories. Information obtained from User Profile is classified into these specified categories. The learning
Abstract — Keyword search is a useful tool for searching large corpuses whose structure is either unknown or constantly changing.RDF is the first W3C standard for enriching information resources of the web with detailed meta data. RDF can be modeled as a directed graph, where nodes are subjects/objects, and edge labels are predicates. The keyword search against an RDF graph looks for a sub graph that has minimum length to connect all the keywords from the common node. The existing approaches for searching is, keywords are mapped to nodes in the graph and their neighborhoods are explored to extract sub graph .Sometimes it lead to zero or less number of subgraphs.To address this issue, we propose a reverse method for searching. The experiment on RDF data shows that proposed method is more efficient.
Commonly used knowledge bases include generic ontologies, thesauruses, and online knowledge bases. The global analysis produce effective performance for user background knowledge extraction but it is limited by the quality of the used knowledge base.
[14] investigated medium type selection as well as search sources for a query. It analyzes question, answer, and multimedia search performance. Then learn a linear SVM model for classification based on the results. 1.1 Question-Based Classification: Since many questions contain multiple sentences and some of the sentences are uninformative. The classification is accomplished with two steps.
In this proposal, present a compelling methodology that catches the client 's calculated inclinations so on provide custom inquiry recommendations. We have a tendency to accomplish this objective with two new methodologies. Within the first place, we develop online methods that focus on concepts from the web-scraps of the item came back from an inquiry and utilize the concepts to acknowledge related inquiries for that query. Then we propose one more phase customized agglomerate combination calculation that can produce custom inquiry cluster. To the most effective of the creators ' data, no past work has attended personalization for question recommendations. To assess the viability of our
In recent years, we observed increasing in online Q&A websites, such as Stack Exchange, Quora, and Yahoo! Answer etc. These websites become a favourite destination for most of internet users, because they are able to asking any question in any field, and share it with community, and then they receive the answer from different sources. User’s questions can be ranking using up or down voting; also user’s answers can be ranking using up or down voting and accepting as correctly or incorrectly answer.
Matching corresponding terms in queries and documents in the corpus is done by conjunction. Due to this, recall is low in case of long queries. We can redevelop such queries to improve the probability of matching corresponding terms in ueries and relevant documents. This process is called query expansion. In this research paper,various models that take as input user query records and output replacements for query terms from terms in the revelent documents, are analyzed. The best outlook to employ while training the model to learn from the training data is also described.