Ontology contains a set of concepts and relationship between concepts, and can be applied into information retrieval to deal with user queries.
Challenges in interpreting a query from different ontologies:
• It is not possible to determine in advance which ontologies will be relevant to a particular query.
• User queried keyword has to be translated into ontology-centric terminologies.
• Answer to a query may require the integration of information from multiple ontologies.
Our approach is to keep the ontologies separate. We assume they use the same description logic, even though not essentially the same vocabulary (i.e. they can use different names for the same concept and/or the same names for different concepts). The aim is to
…show more content…
The natural language query is sent to NL Processing engine where it is processed and is converted to DL query. Stop words are stripped off the queries. NL-DL query convertor comprise of several natural language processing tools such as the Stanford Parser for creating the parse tree while WordNet can be utilized to account for syntactic variability by finding synonymous words. The query processor’s task is providing the user with the best answer to the question from the ontology. High level architecture of the model is shown in figure 1.
Figure 1: High level architecture of MOSS-IR
Query processor system parses the query and interprets the meaning of the end-user’s query terms. This enables the construction of a meaningful query. Before any actual query re-formulation, the mapping between the vocabulary of the ontologies and the query is required. The mapping is indispensable for retrieval improvement using ontology based query approaches. The first step of the processor is to identify the set of ontologies likely to provide the information requested by the user. Hence it searches for near syntactic matches within the ontology indexes, using lexically related words obtained from WordNet [27] and from the ontologies, used as background knowledge sources. It identifies the subject, predicate and object, which is used to generate the DL query and runs it against the ontology to attempt to
Jake Mannix, Lucidworks: In this more technical talk, Jake explained how Lucene scores a query, and what classes are instantiated to support the scoring. Jake described, first, at a high level how to do scoring modification to Lucene-based systems, including some “Google”-like questions on how to score efficiently. Then, he went into more details about the BooleanQuery class and is cousins, showing where the Lucene API allows for modifications of scoring with pluggable Similarity metrics and even deep inner-loop, where ML-trained ranking models could be instantiated - if you’re willing to do a little
Epistemology is concerned with belief rationality, nature, origin, methods, knowledge validity and limits of human knowledge, (Genest, 2004). Following this observation am committed to understanding how the truth about what I know influences my personal beliefs and ideologies. Eventually, my ultimate concern is to justify and verify the little knowledge I possess. According to the school of evidentialism, the evidence is relevant in the justification of belief, (Clark & VanArragon, 2011). Secondly, ontology is concerned with the entities in the universe, and I must understand it to understand the world. Questions ranging
Another method is context search. The context search adds context to the search criteria. “Context search helps improve the keyword search solution by addressing the problems present in keyword searches related to synonymy and polysemy. Synonymy is a common linguistic issue where different words are used to express the same concept, and polysemy is where the same word can have different meanings” (Fordham, 2013). The context search method combines several advance techniques in a simple user interface, making searches
Objective and subjective approach of investigative things forms two important elements of ontology, broadly called as the Positivism and Subjectivism.
Quine in his paper titled “On What There Is” (Kim, Sosa, & Korman, 2012, p. 7-15) aims to provide an account of two different ontologies and suggests that his answer is the better answer to the ontological problem. Ontology deals with the question of what there is. The problem is understanding what the right answer is. In this response, I will explain Quine’s criterion of ontological commitment and his response to McX’s argument for the existence of universals. McX is a fictitious philosopher created for taking a position on an ontology different from his own. Simply put, Quine’s criterion for ontological commitment is that statements must use bound variables because names are not enough to commit us to an ontology. That is to say,
While in search engines user give words key and that search engine compiled such keywords from web page into database which user could query. These search engines continuously update their information to provides the accurate and actual result of users search. Example of search engines includes alta vista,lucos and excite.
Ontology: How the researcher views the world and the assumptions that are made about the nature of the world and of reality.
The structure of the Ontological Argument can be outlined as follows (The argument is based on Anselm's Proslogion 2):
The author had mentioned about the EDM, FTR and the WWW at the first discussion. This had shown that many EDM vendors had to promote the “off the peg” systems. Its means here this system relied on the use of automated indexing for the retrieval purpose. Then, FTR is limited by its reliance on natural language. This is because every different records creator will use different terms in order to show the same or closely meaning. Meanwhile, for the WWW it has great demands and also can facilitate the searching. This can be seen through the “hits” that was produces after conducting a searching.
As part of this endeavour, the ontological status of the core ideas, and the logical structure of the
Identify the sources used to acquire the domain knowledge (ex., experts, documents, existing ontologies, etc.).
In some cases, the ontology can be described as a set of definition of formal vocabulary. Ontologies are also not limited to conservative definition, that is, definition in the traditional logic sense that only introduce terminology and do not add any knowledge about the world (Endeton, 1972).
Basically, the term of ontology is derives from Greek and “onto” meaning and “logos” interpreted as “science”, that’s mean ontology can be understood as a science or study of being. The word can be divided into two senses such as exist an entity thing. Other than that this word is about what to be or to exist. According to Nicola (2009)” the word ontology can be used with different meaning in different communication. John Sowa (1998) study found that subject of ontology is the study of the categories of things that exist or may exist in some domain.
C. Image Based QA: An image-based QA approach was introduced in [11], which mainly focuses on finding information about physical objects. An image-based QA system allows direct use of an image that refers to the object. This type of systems was designed to find multimedia answers from web-scale media resources such as Flicker, Google images. D. Multimedia QA Search: Due to the increasing amount of digital information stored over the web, searching for desired information has become an essential task. The research in this area started from the early 1980s.
In this paper we surveyed the state of the art in multilingual text retrieval accessing parallel web pages. Multilingual search engines typically consist of a crawler which traverses the web, retrieves the required web page in the desire languages. It provides front end user interface, which can be used for selecting language for query submission. The way the query is fired leads into two types of search Cross-language information retrieval and Multi-language information retrieval. In cross-language retrieval the user query is machine translated into multiple language queries automatically as per user selection and then fired. In multi-language retrieval the user has to provide queries in multiple languages to fetch the web documents in different languages. Also in some search engine the web page is machine translated and forwarded to the user. NLP is still in the expansion phase and has to make advances in it, research is going on all over world. Experiment was done with top rated multilingual search engine to access parallel pages but could not find it. When billions of parallel web documents are present on the web in different languages why not explore that? A alternative to that can be searching through parallel pair finder.