News for hackers. Stuff that matters.

A comment on Startup School 2017 First Lecture. Parent comment

Re:Startup School 2017 First Lecture by bootload on Wednesday April 05, 2017 @07:30PM (#14046645)
" it would be interesting to have a diff tool for videos"

    videoA -> transcriptionA
                |
                V
    videoB -> transcriptionB
                |
                V
               diff
[ Parent | on HN ]
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?

[ Parent | on HN ]
Re:Startup School 2017 First Lecture by bootload on Thursday April 06, 2017 @03:06AM (#14048543)
"seems too granular,"

Probably right. I used the term diff as a concept not implementation.

[ Parent | on HN ]