C5W3L06 Bleu Score (Optional)

Follow us:

[epistemophilicmetalhead]

when it comes to translation, there can be >1 correct answers. BLEU (bilingual evaluation) score measures how correct a translation is by comparing it with the translation provided by actual people. modified precision is used to calculate BLEU score
modified precision (word by word) = max number of times the word is supposed to appear / number of times the word is present in the translation.
modified precision on bigrams is where you take two consecutive words at a time (like a slider) and then calculate using the same formula (but for a two word phrase this time)
same goes for n-grams
if the output is exactly equal to one of the references, all modified precision values (for 1, 2, ....n-grams) = 1.0
combined BLEU score = BP*exp(sum of k modified precisions / n) where k goes from 1 to n and BP=brevity penalty (it penalizes translations that are too short because short translations have a higher chance of having higher modified precision scores)
BP = 1 if output (machine translation) length>reference (human translation) length
BP = exp(1- (machine translation length/human translation length)) otherwise

[alignedbyprinciple]

I read other people's tutorials regarding this topic and by far this is the best and easiest tutorial on bleu score. Thanks a lot.

[thedissociation]

Thank you and also your voice is so calming

[shayanhati]

Please upload the full series. Eagerly waiting.

[wenkaidai]

Looking forward to your upload of full series of sequence models~

[Heyoo-vxvt]

I think that brevity penalty factor has to be
if MT_output_length<= reference_output_length
because we have to penalize when the length of the output sentence is too short.

Maybe that is a typo.

[Acha]

at time 8:14 there is a mistake, the count clip for "the mat" should be 2, isn't it.?

[jimmylee]

according to the original paper, does the BP under otherwise condition should be

[anthonyarmour]

Great video, but there's an error I've seen in every resource I've looked at. Had to find out from reading the original paper. Cumulative Bleu score = BP × exp( 1/n x sum(log(Pn))).. the log is an important difference. Video was great tho! I've seen like 5 resources that seem to have left the log out

[therri]

Lecture L03 and L04 are missing from the playlist of the week

[CTimmerman]

0:45 Reference 2 is not perfectly fine.

[RaviCHandra-fjdr]

please upload full series of sequence models. waiting for it.

[annawilson]

Why only up to p_4 n-gram, if there are 6 words in reference #1? Up to p_5 is better, no?

[jimmccarthy]

Will the full series of Sequence Models be uploaded soon?

[veerudumpala]

Brevity Penality Factor:
IF len(MT_output) == len(ref_output)
then also exp(1-m/r) equals to 1? Right?

[chrischappell]

thank for upload this series ... plz add course about natural processing language that pro andrew mention is last past of full series about deeplearn in coursea :)) thk

[SupunKandambige]

1:59 didn't know that he uses Slack

[aqwkpfdhtla]

There is a high pitch sound. It is so annoying.

[alexminsky]

One of the most boring lecturer I’ve ever seen! He’s great, though.

[bnglr]

poorly explained. and the formula is wrong. Andrew is overrated