" it would be interesting to have a diff tool for videos"
videoA -> transcriptionA
|
V
videoB -> transcriptionB
|
V
diff
Re:Startup School 2017 First Lecture
by rahimnathwani on Thursday April 06, 2017 @01:19AM
(#14048126)
That seems too granular, as an additional 'uh' or 'and' would cause a sentence to be seen as different.
It might work well if you can first pair up the similar sentences from A and B, using word-level edit distance, or mapping to a lower-dimensional space using sentence embedding?
"seems too granular,"
Probably right. I used the term diff as a concept not implementation.
Re:Startup School 2017 First Lecture
by garysieling on Wednesday April 05, 2017 @07:12PM
(#14046543)
Can't help with the diff tool concept, but I built a search engine for talks, which semi-randomizes the results to force a variety in the search results.
For business talks, you can see it here: http://findlectures.com/?p=1&type1=Conference&talk_type_l2_C...
This includes the older startup school talks, plus a few good software business conferences. For the next phase, I want to highlight talks that are most unique to the category (using word lists in the transcript/captions, not video diff)
Re:Startup School 2017 First Lecture
by ChajusSaib on Wednesday April 05, 2017 @06:53PM
(#14046427)
Could you link the other one, thanks!
Which makes me think: it would be interesting to have a diff tool for videos, but it diffs a representation of the content not specific video frames.
Customers might include all the students of Udacity, Coursera, EdX and Startupschool.