Show HN: QuoDB – Movie quote search engine based on subtitles
quodb.com
quodb.com
Terminator:
"nothing clean right" - no results
"fuck you, asshole" - one result for Terminator, but the phrase occurs twice in the film.
Predator:
"If it bleeds, we can kill it" - Predator came up, and a few others (interesting).
Total Recall:
"Sue me, dickhead" - it got that one.
Commando:
"You're a funny guy Sully, I like you. That's why I'm going to kill you last." - no results.
I'm probably gonna spend all night on this.EDIT: reformatted.
[1] http://www.slate.com/articles/technology/technology/2009/03/...
We used this as the basis to train a speech-to-text engine by automatically correcting likely-wrong interpretations. "I go loo school" would be corrected to "I go to school", for example. It worked remarkably well.
The basis of all these subtitles can be used, but there are far bigger (and better?) collections of data to be used to train these machine learning engines.
http://www.quodb.com/#search/you%20look%20like%20shit
531 titles. Wow.
http://www.quodb.com/#search/we've%20got%20company
Incoming is the moral equivalent (and is much more popular), but is less impressive since it's only one word.
http://www.quodb.com/#search/i%20want%20you%20to%20hit%20me%...
So while the fuzzy matching is neat, sometimes it's handy to be able to perform an exact search as well.
Typically this is done using "quotation marks" around the search term(s).
What is it using localStorage for? Without dom.storage.enabled, it's just a blank white page with a footer.
Also posted to HN not too long ago