Question answering is an information retrieval approach where a computer program finds the best answer to a user’s natural language question. Programs require a database and can handle complex questions. They can learn from user feedback and improve over time.
Question answering is an approach to information retrieval in which a user asks a question in natural language and a computer program finds the most appropriate answer. A number of programs that have this feature have been developed by researchers and organizations from around the world, and many are open to the public who want to experience them. The ability to use natural language processing to retrieve information can be critically important for a variety of tasks, from searching for university papers to compiling specialized technical knowledge.
Every question answering program needs a database of information to draw upon. Some programs focus on data within a specific domain, such as medical publications or engineering documentation. In some cases, the system may focus specifically on information stored at a particular organization. Others are “open domains” and can pull data from a variety of sources using the Internet.
The process begins when the user asks a question. Natural language processing programs can quickly break a question into components to determine what type it is and how to find the best answer. Some systems are capable of handling complex, multi-part questions, such as telling the user the difference between two things or answering a question that has a dependent clause, such as “Are there requirements to be an airline pilot and, if affirmative, what are they?”
Such programs can build a quick tree of question types which they use to determine the best reference or references to use to answer the question. They may also sift through conflicting or competing data, such as sources that provide multiple dates for a historical event. The program may determine that some sources are not accurate or it may find that sources use different dating systems, accounting for the disparity. A highly intelligent question answering system may be able to provide additional resources and context to help the reader understand the answer.
One use for answering questions is in responding to quick questions asked by users who simply need a quick reference, such as a book’s publication date or a city’s population. Others can retrieve documents and associated searches on command. They could also perform specialized functions such as searches of patent databases for use in patent investigations.
Over time, the system can learn from its users. A question answering program might ask the user if an answer is relevant or helpful, then store this information for future reference. Users might also be able to redirect or fix the system when it makes a mistake. Over time and with many uses, the program will become more adept at answering questions.
Protect your devices with Threat Protection by NordVPN
