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? Could they try to Crawling FAQs to get answers?
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 by crawling FAQs, 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 a question and answer pairs. The processes that they then use on those question and answer pairs, to make them useful for Question Answering are 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? If you thought a search engine might be crawling FAQ pages, would you make more of an effort?
Some posts I’ve written about patents involving question answering:
- 7/19/2007 – Search Engines Crawling FAQs to Learn How to Answer Questions?
- 9/21/2014 – Google May Use Question Answering to Populate the Knowledge Graph
- 10/12/2014 – How Google May Use Entity References to Answer Questions
- 12/30/2014 – Featured Snippets – Taken from Authority Websites
- 12/31/2014 – Feature Snippets – Using Query Intent Templates to Identify Answers
- 2/11/2015 – How Google was Corroborating Facts for Featured Snippets
- 7/12/2015 – How Google May Answer Questions in Queries with Rich Content Results
- 9/9/2015 – When Google Started Showing Featured Snippets
- 11/30/2016 – Answering Featured Snippets Timely, Using Sentence Compression on News
- 6/19/2017 – Google Extracts Facts from the Web to Provide Fact Answers
- 7/10/2019 – How Google May Handle Question Answering when Facts are Missing
Last Updated July 11, 2019.
I think I search much the same way you do Bill, though lately I have been finding myself typing more real questions when I’m not getting the results I want.
Forums have been a great source for me in answering specific questions and I think you can add them to FAQ pages. It should be reasonable easy for a search engine to determine when a question is being asked in a query through either a question mark at the end or a who, what, where, why, how, etc at the beginning.
It might not be a bad idea to give certain types of pages suck as FAQs and forum threads (and I’m sure others) a boost when it’s been determined the query is a direct question.
This looks like it may have something to do with Google’s multi-language search functionality. It’s certainly an interesting advance in semantic search.
It would be interesting to see if forums could be incorporated into a method like this, Stephen.
The paper does provide some interesting experiments and results involving paraphasing questions in different languages, Michael. The reseach they conducted does go beyond the scope of Question Answering. I checked through the publications of some of the authors to see if there were any papers moving more in that direction. Didn’t see any, but it may be worth keeping an eye out for.
I think you’ve spotted an angle, before anyone else I’ve read, that will become an increasingly important aspect of SEO for semantic search.
Bill – thank you.
Thanks, Gideon.
It’s an area that is probably worth paying a lot more attention to in the future. How much will machine translation affect future search? I know I’ll be tracking it as closely as I can.
I think that most people when searching for specific information they type it as a question(as if they are talking to a person) and they expect the search engine to return with the best answers for their question, and so this idea for searching the FAQs pages is a very good idea but it needs the webmasters to really think about the questions(the words to use) and to put a very clear answer.
btw thanks for the useful post
Hi Learn How,
Thanks – those are good points. I guess not everyone searches the same way, but for people who do search by asking questions, I think the approach being described in this paper may just help.
I agree completely with you about how important it is for webmasters to think carefully about the words that they use on their pages – trying to make sure that they use language that people searching for information on their pages might also use.