Be nice to merge it with a 2gram corpus sorted by frequency, so that word pairs that simply don't occur in English (like "autonomous frown", "voice glockenspiel", "harp speedboat") are less likely to be shown than words that might conceivably make sense.
Another idea might be to POS tag the words and only present verb noun combinations, but you'd have to play around a bit to see which parts of speech rendered the best domains.
Anyway, here are some nice sounding domains I've found with this tool:
historicalreading.com
brokencurrency.com
bagelmoon.com
sofacake.com
dancebrick.com
wholesalerreport.com
slimyslime.com (if you're a slime retailer, this is a perfect domain!)
and some not-so-good ones:
tramprugby.com (I would pay to see this)
aftershavejustice.com
beanslime.com
depressedtuesday.com (can we make this a national holiday?)
I've done this before. You're right. The CPU intensive part is the word search itself. Building the combinations and finding adjacent words, which you've already done. The ngram piece is straightforward by comparison. Just compare the domain (with any hyphens removed) against a dictionary of concatenated ngrams. You'll have to veryify that any hyphens occur on word breaks afterwards, but it's a small price to pay for the simplicity of a string compare (or key lookup). You will probably want to load all of your ngram dictionaries into memory, though, or the search will be horribly slow.
I have already done this, but it is difficult to squeeze the running algorithm memory. The current POS solution uses only 400MB memory. Also, 2grams are not that good as collocations.
That's interesting, because I think word pairs that simply don't occur in English could be a feature also. Maybe an on-off switch. I kind of like the domain voiceglockenspiel. Although several of your listed nice-sounding domains also seem to be pairs that simply don't occur in English as well?
Awesome! Definitely some good and funny domain name suggestions in there.
One thing though: When searching for a word, such as "reed", it discovers domains that have two different words that spell "reed" when placed together such as "TreeDaisy.com". For the example "reed", I also get a lot of results like "AgreedSummer.com" where the word I'm searching for makes up a different, unrelated word.
Besides "reed" here's another example "fee". It gives me feel and feet and even coffee. I'd also like to search for a specific word and not part of other words.
Feedback: It is a little bit frustrating being able to see only 10 per page. It makes me think about scrapping the site for the keywords that I am interested.
Good job. Some cool domains there, added to tools bookmark.
Note that currently the word list is not that big (~2400 nouns), we'll be adding more based on search terms so if the search gives you empty page you might want to try again in few days.
I like the site. If a search returns no results you might want to alert the user of this (i.e. 'no results found' or something similar). I couldn't tell if it just wasn't loading or if my search actually didn't get any matches.
Not sure how the search works. I searched for 'amortize', 'amortization' etc. because I am looking to host a script that generates amortization schedule. Nothing returned.
Take the words for the domain, so "airport smell" for airportsmell.com (yes that was one of the random domains heh). Then do a search on Google for the phrase, and fetch the number of results as a 'score'.
I'd be interested to see if this can pluck out "better" names from the pile.
Another idea might be to POS tag the words and only present verb noun combinations, but you'd have to play around a bit to see which parts of speech rendered the best domains.
Anyway, here are some nice sounding domains I've found with this tool:
historicalreading.com
brokencurrency.com
bagelmoon.com
sofacake.com
dancebrick.com
wholesalerreport.com
slimyslime.com (if you're a slime retailer, this is a perfect domain!)
and some not-so-good ones:
tramprugby.com (I would pay to see this)
aftershavejustice.com
beanslime.com
depressedtuesday.com (can we make this a national holiday?)