spell fixes

graviraja · Aug 5, 2020 · bd2acd6 · bd2acd6
1 parent 2923288
commit bd2acd6
Show file tree

Hide file tree

Showing 4 changed files with 6 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -451,13 +451,13 @@ A CRF calculates not only the emission scores but also the `transition scores`,
 
 ![ner](assets/images/applications/classification/bilstm_crf.png)
 
-### Day 81: NER Decoding using Vitebri Algorithm
+### Day 81: NER Decoding using Viterbi Algorithm
 
-For decoding, `Vitebri` algorithm is used.
+For decoding, `Viterbi` algorithm is used.
 
 Since we're using CRFs, we're not so much predicting the right label at each word as we are predicting the right label sequence for a word sequence. Viterbi Decoding is a way to do exactly this – find the most optimal tag sequence from the scores computed by a Conditional Random Field.
 
-![ner](assets/images/applications/classification/vitebri.png)
+![ner](assets/images/applications/classification/viterbi.png)
 
 Checkout the code in `applications/classification` folder
 

diff --git a/applications/classification/README.md b/applications/classification/README.md
@@ -154,6 +154,6 @@ Without a CRF, we would have simply used a single linear layer to transform the
 
 A CRF calculates not only the emission scores but also the `transition scores`, which are the likelihood of a word being a certain tag considering the previous word was a certain tag. Therefore the transition scores measure how likely it is to transition from one tag to another.
 
-For decoding, `Vitebri` algorithm is used.
+For decoding, `Viterbi` algorithm is used.
 
 Since we're using CRFs, we're not so much predicting the right label at each word as we are predicting the right label sequence for a word sequence. Viterbi Decoding is a way to do exactly this – find the most optimal tag sequence from the scores computed by a Conditional Random Field.
diff --git a/applications/classification/ner_tagging/README.md b/applications/classification/ner_tagging/README.md
@@ -49,11 +49,11 @@ Probability of a tag depends on the input and previously predicted token:
 
 ![ner](../../../assets/images/applications/classification/bilstm_crf.png)
 
-For decoding, `Vitebri` algorithm is used.
+For decoding, `Viterbi` algorithm is used.
 
 Since we're using CRFs, we're not so much predicting the right label at each word as we are predicting the right label sequence for a word sequence. Viterbi Decoding is a way to do exactly this – find the most optimal tag sequence from the scores computed by a Conditional Random Field.
 
-![ner](../../../assets/images/applications/classification/vitebri.png)
+![ner](../../../assets/images/applications/classification/viterbi.png)
 
 #### Resources
 

diff --git a/...s/applications/classification/vitebri.png → ...s/applications/classification/viterbi.png b/...s/applications/classification/vitebri.png → ...s/applications/classification/viterbi.png