Hello,
I noticed some mistranscriptions in the transcript (subtitles, captions) for the course videos. Below is the errata for the 2nd week.
The format for the errata is as follows. The approximate time is in braces, then the mistranscribed word or phrase follows, followed by a hyphen, then followed by the correct word or phrase. Like this:
[time] mistranscribed word or phrase - correct word or phrase
video - Markov chains
[2:20] does - that
video - Markov chains and POS tags
[0:39] announce - nouns
[0:56] less - last
[2:53] announced - a noun
[3:14] These some - The sum
video - hidden Markov models
[2:47] end - N
video - calculating probabilities
[2:43] and the divisor - in the divisor
[2:48] shorts - short
[3:37] and nicely - a nicely
video - populating the transition matrix
[1:20] verbalize high cool - verbless haiku
[3:12] in lots - a lot
[3:21] high cools - haikus
[4:25] and a real - in a real
video - populating the emission matrix
[0:32] sags - tags
[0:49] stack - tag
[1:11] tax - tags
[1:27] non - noun
[1:46] be - P
[1:50] attack - tag
[1:57] rows in - row sum
[2:29] confuse - compute
video - Viterbi algorithm
[1:27] verb state NN - verb state VB (here the lecturer misspeaks)
[2:30] spot - path
[3:42] matrix B - matrix D
video - Viterbi: backward pass
[1:02] index as - index s
[4:19] t,i - t_i
video - week conclusion
[0:05] don’t - now
[0:16] target has - target task
[0:28] thing - team
[0:36] piers - tears
[0:55] how to complete - auto-complete