View stunning SlideShares in full-screen with the new iOS app!Introducing SlideShare for AndroidExplore all your favorite topics in the SlideShare appGet the SlideShare app to Save for Later — even offline
View stunning SlideShares in full-screen with the new Android app!View stunning SlideShares in full-screen with the new iOS app!
Semantic technology Presented By Rashmita Pradhan Branch:CSE(A) Regd.no.0601214013 Sem:7th
introduction semantic technology: Encodes meanings. Enables machines & people to share & understand with each other. Why semantic technology is to be used?? Ans: With traditional information technology, meanings and relationships must be predefined &“hard wired” into data formats and the application program code at design time. .
Semantic technologies are “meaning-centered.” They include tools for:- 1.autorecognition of topics and concepts. 2.information and meaning extraction. 3.categorization
What is Semantic search ? Semantic search Process to improve online searching. Disambiguates queries & web text. Two major forms of search: Navigational Research Semantic Search lends itself well in research search. Semantic Search uses semantics, or the science of meaning in language to produce highly relevant search results. the goal is to deliver the information queried by a user.
Search engine works on?? Search engine works on NLP(Natural Language Processing). NLP is the technology that evaluate the relationship of words such as actions,entities, events,comprising within unstuctured text meaning sentences within paragraphs found in variety of text based document. Question answering NLP search is the NLP technology that specifically solves the problem of finding answer to the question which can be asked by simply entering it into a search interface using Natural Human Language. NLP question answering search specifically allows users to ask question in their natural language and then retrieve most relevant answer within seconds.
NaturalLanguage Processing and Semantics To process a text analysis, the Semantic Engine operates in 6 stages: Sentence and Proposition Hashing, Ambiguity Solving (with respect to the words of the text), Identification of Equivalent classes (senses), Statistics, detection of Bundles and Episodes, Detection of the Most Characteristic Parts of text, Layout and display of the result.
To simplify the analysis, the Semantic Engine divides the text into propositions .
This first stage is based on a scrutiny of the punctuation, and on a complex process of syntax analysis.
This yields highly reliable co-occurrence statistics (Relations).
Propositional hashing is bound to involve errors (propositions that are either too short or too long), but this does not affect the results.
Ambiguity solving (Semantic and Lexical Analysis) The automatic interpretation of words in any living language, either written or spoken, requires the solving of numerous ambiguities: grammatical and syntactic: Semantic:
Words are grouped together in several main word categories. Among these, six are of interest to us: Verbs, Connectors (conjunctions, conjunctive phrases), Modalities (adverbs or adverbial phrases), Qualifying Adjectives, Personal pronouns, Substantives and Proper Nouns
Use of Word categories (Text Analysis) We can say that: time and place connectors and modalities provide the means to locate the action, intensity and negation modalities provide the means to dramatize the discourse, cause and condition connectors provide the means to construct a chain of reasoning, addition connectors provide the means to enumerate facts or characteristics, opposition connectors more specifically provide the means to argue, to put things into perspective and to set out conflicting standpoints.
References and Relations (Semantic Analysis) The Equivalent Classes constitute groups of closely related meanings (common nouns, proper nouns, trademarks, etc.) appearing frequently throughout the text. The Reference Fields group together the words comprising the Equivalent Classes in order to enable the software to build up a representation of the context. To achieve this, the Semantic equivalents dictionary of Tropes is composed of three different classification levels. At the lowest level are the References, which are next merged more broadly into Reference fields 2, which, in turn, are merged into Reference fields 1.
Bundles and Episodes (Chronological Analysis) Tropes employs two different tools to study the chronology of a discourse. This analysis is based on two notions: Bundles Episodes Most characteristic parts of text: The contraction of the text reveals the Most Characteristic Parts of text. These are "propositions introducing main themes or characters, expressing events that are essential to the progression of the story (causal attributions of consequences, results, aims)".
list of NL search engines: Ask.com Brainboost Lexxe Hakia Haika
Future of semantic search technology Enables accurate retrieval of information. Effective technology Can be appropriately applied to credible and dynamic content
conclusion The World Wide Web has certain design features that make it different from earlier hyperlink experiments. These features will play an important role in the design of the Semantic Web. The Web is not the whole Internet, and it would be possible to develop many capabilities of the Semantic Web using other means besides the World Wide Web. But because the Web is so widespread, and because it's basic operations are relatively simple, most of the technologies being contemplated for the Semantic Web are based on the current Web, sometimes with extensions. One day technologies will forecast the future studying the present.