People do type questions into search engine search boxes and expect meaningful answers.
The best search results aren’t always found based upon matching the words in the questions to pages that might also contain those questions or similar questions. What strategies might be used by the search engines to provide a good user experience?
A paper from Google researchers on Question Answering, Statistical Machine Translation for Query Expansion in Answer Retrieval (pdf), looks at automated strategies for understanding and answering questions that people might type into a search box.
I’ve been finding answers on how to do things on the web for years, by looking for frequently asked questions (FAQs) pages, and tutorials. Usually those searches involve using those words (FAQ or tutorial) in my queries, along with a couple of words related to what I want to learn how to do.
For example, to join words together from one box in excel to another, I might type into Google the following:
concatenate excel tutorial
Less frequently, I’ll type in an actual question into a search engine box, to try to find an answer, but it seems that people do ask questions of search engines.
Can a search engine use the strategy that I employ – looking at FAQ pages, and use those frequently asked questions to try to understand relationships between words in questions, and words in answers on those pages, to understand queries in question form, and try to provide answers to those questions?
The paper explores the use of a database of FAQ pages, which they found through “intitle:faq” and “inurl:faq” queries in the search engine, to come up with question and answer pairs. The processes that they then use on those question and answer pairs, to make them useful for Question Answering are definitely worth a look.
When you write a set of questions for a Frequently Asked Questions page, how much effort do you take in trying to craft those questions, and in choosing the words used within them?