Rich Lexical Knowledge based Q&A System for Ubiquitous Knowledge Service (original) (raw)
Related papers
Knowledge Baesd Question Answering System Using Ontology
In the modern era numerous information available in the World Wide Web. Question Answering systems aims to retrieve point-to-point answers rather than flooding with documents. It is needed when the user gets an in depth knowledge in a particular domain. When user needs some information, it must give the relevant answer. The basic idea of QA systems in Natural Language Processing (NLP) is to provide correct answers to the questions for the user. Here the question answering system has to be implemented as semantic web. This research will evaluate the answering system by the expert. The experts are personalized based on their domain and subject. Ontology is used to personalize the experts. Based on these, the answer has to be ranked and given back to the user. It consists of three phases such as User’s zone, Interface and Expert’s zone. Natural language processing techniques are used for processing the question and also for answer extraction. The domain knowledge is used for reformulating queries and identifying the relations.The highlight of this paper is providing most relative answer for the question provided by the end users in an efficient way.
Ontology-driven question answering system with semantic web services support
Nowadays the internet is becoming a huge dump of documents, links and all other sorts of information. Most common possibilities to explore this information are information retrieval applications such as web search engines. Despite the fact that search engines are doing an excellent job, they still return too much inaccurate information. The solution to this problem can be found in the form of question answering systems, where the user gives a question in natural language, similarly to talking with another person. The answer is the exact information instead of a list of possible results. This paper presents the design of our ontology-driven question answering system with semantic web services support.
A question answering system on domain specific knowledge with semantic web support
2011
In today's world the majority of information is accessible via the World Wide Web. A common way to access this information is through information retrieval applications like web search engines. We already know that web search engines flood their users with enormous amount of data from which they cannot figure out the essential and most important information. These disadvantages can be reduced with question answering systems. The basic idea of question answering systems is to be able to provide answers to a specific question written in natural language. The main goal of question answering systems is to find a specific answer. This paper presents an architecture of our ontology-driven system that uses semantic description of the processes, databases and web services for question answering system in the Slovenian language.
Architecture of an Ontology-Based Domain-Specific Natural Language Question Answering System
International journal of Web & Semantic Technology, 2013
Question answering (QA) system aims at retrieving precise information from a large collection of documents against a query. This paper describes the architecture of a Natural Language Question Answering (NLQA) system for a specific domain based on the ontological information, a step towards semantic web question answering. The proposed architecture defines four basic modules suitable for enhancing current QA capabilities with the ability of processing complex questions. The first module was the question processing, which analyses and classifies the question and also reformulates the user query. The second module allows the process of retrieving the relevant documents. The next module processes the retrieved documents, and the last module performs the extraction and generation of a response. Natural language processing techniques are used for processing the question and documents and also for answer extraction. Ontology and domain knowledge are used for reformulating queries and identifying the relations. The aim of the system is to generate short and specific answer to the question that is asked in the natural language in a specific domain. We have achieved 94 % accuracy of natural language question answering in our implementation.
OPEN DOMAIN QUESTION ANSWERING SYSTEM USING SEMANTIC ROLE LABELING
The World Wide Web is an attractive source of information retrieval and can be used for seeking simple factual answers for user questions. Although usual information retrieval systems like search engines helps in finding the relevant documents for a set of keywords, there are situations where we have more specific information need. Search engines only provide the actual facts as a ranked list of documents and links that contain the keywords. However, what a user really wants is often a precise answer to a question. A Question Answering system gives us a precise solution to this scenario. A Question Answering system retrieves a precise answer to any natural language question posed by the user. A typical QA system uses several language processing techniques. In this paper, an Open Domain Question Answering that answers simple Wh-questions using online search has been proposed.
The development of a question-answering services system for the farmer through SMS
Proceedings of the 2009 Workshop on Knowledge and Reasoning for Answering Questions - KRAQ '09, 2009
In this paper, we propose the development of the Question-Answering Services System for the Farmer, through SMS, by focusing on query analysis and annotation based on a similar technique previously applied to language generation, thematic roles, and primitive systems of the Lexical Conceptual Structure (LCS). The annotation places emphasis on the semantics model of "What" and "How" queries, lexical inference identification, and semantic role, for the answer. Finally, we show how these annotations and inference rules contribute to the generalization of the matching system over semantic categories in order to have a large scale question-answering system.
Ontology-based Question Answering System
Data and Information requirement is increasing with the Increase in the volumes of data in the repositories such as www etc, now question arises that out of this enormous data how to find the information which is required by the user and should be specific in nature. Information retrieval techniques solves the problem to an extent but they cannot help in a situation where only specific information pertaining to a question is required. Information retrieval engines will retrieve documents containing phrases and paragraphs which may have an answer to user query. This problem is addressed in this research paper which proposes a question answering system to satisfy users specific information need.
A Review Paper: Question and Answering System
International Journal of Computer Applications, 2013
It is examined that the power of ontology based for open and closed domain question and its answering systems in this paper. In the order of obtaining an optimal database for this system, it has studied the method for linking the different phrases of different web links. The tagged corpus is built from an Internet in the bootstrapping process by providing some of the handcrafted examples of each question and their types. And then the patterns are automatically extracted from the returned documents and formatted answers are provided according to the entities and keywords provided. The precision of each entity has been calculated, and the each question type's average. This ontology is then applied to find the answers of new questions which are about to ask.
Advances in Intelligent Systems and Computing
The rising popularity of the Information Retrieval (IR) field has created a high demand for the services which facilitates the web users to rapidly and reliably retrieve the most pertinent information. Question Answering (QA) system is one of the services which provide the adequate sentences as answers to the specific natural language questions. Despite its importance, it lacks in providing the accurate answer along with the adequate, significant information while increasing the degree of ambiguity in the candidate answers. It encompasses three phases to enhance the performance of QA system using the web as well as the semantic knowledge. The WAD approach defines the context-aware candidate sentences by using the query expansion technique and entity linking method, second, Ranks the sentences by exploiting the conditional probability between the query and candidate sentences and the automated system, third, identifies the precise answer including the reasonable, adequate information by optimal answer type identification and validation using conditional probability and ontology structure. The WAD methodology provides an answer to a posted query with maximum accuracy than baseline method.
Using ontology in query answering systems: Scenarios, requirements and challenges
2003
Abstract. Equipped with the ultimate query answering system, computers would finally be in a position to address all our information needs in a natural way. In this paper, we describe how Language and Computing nv (L&C), a developer of ontology-based natural language understanding systems for the healthcare domain, is working towards the ultimate Question Answering (QA) System for healthcare workers.