Notice of Violation of IEEE Publication Principles: Question answering system: A survey

Abstract

Question answering (QA) is new research domainin the field of Information Science comes into focus in last few decades. Question answering systems are pretty much different from web based search engines which works on the principal of Information Retrieval(IR), however QA systems works on the concept of Information Retrieval (IR) as well as Information Extraction (IE). Web based search engines takes user's query in natural language and responds the same with references and URLs of related documents and websites, but they failed when a user wants precise answer for their query. By considering these limitations of search engines people finds that there is a need for such a system which answer the user's query rather responds with references or URLs of related documents. User should be provided with the precise answer to their question. They are one step ahead of web search engines which provides relevant documents against users query however QA system provides precise answer. A QA system comprises of three core components question classification, information retrieval and answer extraction module. Answer extraction module distinguishes QA system from web search engines. Question classification module plays an important role in QA since it identifies the type of information user have asked for. Similarly information retrieval is also important, because if none of the retrieved document contains answer sets no further processing can be done.

Survey on Answer Validation for Indonesian Question Answering System (IQAS)

“…[3] [4]. Unfortunately for Indonesian, it is still rarely explored whereas Indonesian is the official language used more than 250 million people.…”

“…Nevertheless, the research of IQAS relatively stable because it was done almost every year except in 2009. Meanwhile, most researches on IQAS were conducted in 2011. finding technique instead of answer validation whereas it is one of the important task in Answer-analysis [4]. Therefore, one of the suggestion to the IQAS community is how to conduct exploration answer validation for Indonesian language.…”

“…Although the results of the search engine are quite good, sometimes users want to obtain answers quickly and directly without open the links that provided by the search engine [2] [3]. Fortunately, research in Natural Language Processing (NLP) developed a system known as Question Answering System (QAS) which is a system processing queries in natural language and can provide direct answers to the user [4].…”

Improving Question Answering System based on a Hybrid Technique

“…However, most of the QA researches are diverse in their scope, design, approaches and evaluation metrics etc. They follow the same basic architecture of QA system (Mathur and Haider, 2015). In general, a typical QA system consists of three modules (phases): Question processing, document processing and answer processing.…”

“…This phase are needed to rank and validate candidate answers which is classified into two general types is of factoid and non-factoid. Figure 1 displays the core component of the three modules of QA system (Mathur and Haider, 2015).…”