The majority of all human knowledge is solely represented in natural language. This knowledge is accessible for humans, who can understand the natural language texts and answer questions about them, but it is not in the same measure accessible for machines. In this section we have listed some basics of question answering outlines:
Question answering system : Overview
Quality and reliable question answering system (QA) would be of high use in various fields. Just imagine, a doctor being able to provide diagnose in a matter of seconds, only by asking his computer a couple of questions about symptoms or a programmer coming with a command right away, without need to read extensive manuals or documentation. Even less specialized tasks, common for our daily life, like looking for a cooking recipe, finding out how to treat a plant, looking up common knowledge or an equation, asking for coordinates to a nearest restaurant. Today, we usually do a web search to find an answer to any of these questions. It is certainly significantly faster than looking for an answer in books, but still, it’s far from perfect. Web Search Engines usually require us to insert our question (or query) not in a way we would ask it another person, but as a set of keywords or sentences describing the answer. After we do that, we still need to look for the answer in the article (sometimes more articles) or even alter our query because it wasn’t accurate enough. This process can sometimes be counter intuitive and time consuming.
Question answering system : Definition
Question answering (QA) is a relatively new area of research. QA is retrieving answers to questions rather than information retrieval systems (search engines), which retrieve documents. This means that question answering systems will possibly be the next generation of search engines. What is left to be done to allow QA to be the next generation of search engines? The answer is higher accuracy, which can be achieved by investigating methods of questions answering. Question answering is the field of science basically dealing with information retrieval and natural language processing. The objective of information retrieval is to search for the elements in the resource that map with user’s specified need, while the objective of natural language processing is to create an environment for the dialog between the user and the system in natural language.
“Question answering (QA) is an application area of computer science which attempts to build software systems that can provide accurate, useful answers to questions posted by human users in natural language (e.g. English)”.
General Architecture of QA
A general QA system architecture consists of three distinct modules which are shown in figure 1, each of which has a core component beside other supplementary components:
Figure 1: Question Answering System Architecture
“Query Processing Module” whose heart is the question classification, the “Document Processing Module” whose heart is the information retrieval, and the “Answer Processing Module” whose heart is the answer extraction. Question processing is the module which identifies the focus of the question, classifies the question type, derives the expected answer type, and reformulates the question into semantically equivalent multiple questions. Reformulation of a question into similar meaning questions is also known as query expansion and it boosts up the recall of the information retrieval system. Information retrieval (IR) system recall is very important for question answering, because if no correct answers are present in a document, no further processing could be carried out to find an answer.
Precision and ranking of candidate passages can also affect question answering performance in the IR phase. Answer extraction is the final component in question answering system, which is a distinguishing feature between question answering systems and the usual sense of text retrieval systems. Answer extraction technology becomes an influential and decisive factor on question answering system for the final results. Therefore, the answer extraction technology is deemed to be a module in the question answering system.
Typically, the following scenario occurs in the QA system:
- First, the user posts a question to the QA system.
- Next the question analyzer determines the focus of the question in order to enhance the accuracy of the QA system.
- Question classification plays a vital role in the QA system by identifying the question type and consequently the type of the expected answer.
- In question reformulation, the question is rephrased by expanding the query and passing it the information retrieval system.
- The information retrieval component is used to retrieve the relevant documents based upon important keywords appearing in the question.
- The retrieved relevant documents are filtered and shortened into paragraphs that are expected to contain the answer.
- Then, these filtered paragraphs are ordered and passed to the answer processing module.
- Based on the answer type and other recognition techniques, the candidate answers are identified.
- A set of heuristics is defined in order to extract only the relevant word or phrase that answers the question.
 Pavla, Matej, “Automatic question answering system” Dissertation Master Thesis, Masaryk university, Faculty of Informatics (201 4) http://is. muni. cz/th/418138/fi_m, 2014.
 S. I. A. Saany, A. Mamat, A. Mustapha, L. S. Affendey, “A Strategy for Question Interpretation in Question Answering System”, International Journal of Computer Science and Telecommunications, Vol. 4, No. 5, pp. 38-43, 2012.
 David Ferrucci, “Towards the open advancement of question answering systems”, IBM, Armonk, NY, IBM Research Report (2009)
 S. Stoyanchev, Y. Song and W. Lahti, “Exact phrases in information retrieval for question answering”, in Proceedings of the 2nd workshop on Information Retrieval for Question Answering, 2008.