Question answering (QA) vs Chatbots

Chatbots and Q&A systems differ in their complexity as well as use cases. Let's discuss each of them separately.

Chatbots:

They can answer various questions asked during an interactive conversation. Interactive conversion means the system keeps a track of questions asked earlier and can engage in longer conversations. They have a sought of memory which helps answer in a more friendlier manner. Also, they retrieve information such as weather, stock prices from various sources. Hence, their ability is far beyond Q&A systems in this sense.

Examples could be Google Assistant, Alexa, Siri.

Q&A Systems:

They are programmed to answer questions only from a particular source of information of sometimes questions belonging to a common topic. The "Ask a question" dialog found on most websites is an example of such a system. They could be thought of a search engine which only works for a specific topic.

For instance, a Q&A system present on

Question-answering (QA) is sometimes used to refer to the task where the input to the system is a question and a list of possible answers (normally only a handful) or a paragraph where the answer is supposed to be found, and the expected answer is the index of the correct answer or the start/end positions where the answer located within the text.

In chatbots, the task is normally defined more generically as "answer the given question". This can be approached in many ways, like with chit chat chatbots, where you simply train your system with pairs of question and answer much like a machine translation system, or with information retrieval chatbots, which make use of documents to identify the relevant pieces of composes the answer based on them.

Therefore, in the usual QA definition, QA is much more constrained (i.e. easier) than chatbots.