Question reformulation based question answering environment model
- PDF / 1,559,063 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 15 Downloads / 286 Views
ORIGINAL RESEARCH
Question reformulation based question answering environment model Irphan Ali1
•
Divakar Yadav2
Received: 14 January 2019 / Accepted: 18 July 2019 Bharati Vidyapeeth’s Institute of Computer Applications and Management 2019
Abstract For effectual information retrieval through Question Answering framework, it is essential to rightly reformulate the questions with respect to expected answers. We designed question answering environment model, based on question reformulation technique, in view of expected answer type for effective question answering. In the proposed model, an agent work in between the user and a semantic web based framework for question answering system and figures out how to reformulate questions to inspire the most appropriate answers. The model utilizes the criteria for ‘‘Total Answer Relevance Score’’ for finding the appropriate answer, returned by the framework. Analyzing the proposed model, it has been observed that the model has produced promising outcomes than the current frameworks based on question reformulation. Keywords Question answering (QA) Natural language (NL) Semantic web (SW) Knowledge base (KB)
1 Introduction These days, Web and web-based social networking have turned out to be the primary source of information. Due to the increase in the modernity of the resources, user’s expectations and information searching activity have & Irphan Ali [email protected] Divakar Yadav [email protected] 1
Uttarakhand Technical University, Dehradun, UK, India
2
Madan Mohan Malaviya University of Technology, Gorakhpur, UP, India
increased. Users expect direct responses to their complex queries apart from data recovery, navigation, and factual question answering. To get such responses, various iterations, evaluations, and synthesis are to be performed [3]. There are many approaches to formulate a user query yielded by the efficiency of natural language [1]. Despite complex data needs, people beat vulnerability by formulating user queries, issuing various searches, and aggregating responses. Motivated by people’s ability to pose correct questions, we introduce the concept of an agent that figure out how a user should fire the right question. The agent is in between the user and backend, semantic web-based framework for question answering (SWFQA) that we call ‘‘Environment’’. An agent aims to boost the possibility of finding the appropriate response by sending a reformulated query to the environment. The agent tries to find the most appropriate answer by posing numerous queries and returned the responses. The internal components of the ‘‘Environment’’ cannot be accessed by the agent, so it must figure out how to test environment like a black box ideally utilizing only queries. The main component of the question answering environment model (QAEM) agent is question reformulator which reformulates the question posed by the user and environment returns the appropriate response to the user. We assess our proposed QAEM on ‘‘eLearning’’ dataset. The QAEM tests the abil
Data Loading...
