Michael Higgins comments

Results 36 comments of


                                            Michael Higgins

fix for word_tokenize() Failing to Split English Contractions When Followed by [\t\n\f\r]

@ekaf Thank you for the suggestions. Do you need some test cases as well? I know some repos want test cases added with every bug fix.

KneserNeyInterpolated has problem with OOV words during testing and perplexity is always inf

I will look into this. I get the same error as well.

KneserNeyInterpolated has problem with OOV words during testing and perplexity is always inf

I tried some things and this is what I got. the second set of numbers is MLE # none out of context # 1.3831080559223603 # 0.4679138720730883 # inf # inf...

KneserNeyInterpolated has problem with OOV words during testing and perplexity is always inf

This also might be related to issue #2727

Reimplementing Monolingual Word Aligner in NLTK

Hi, there are instructions in the readme

problem with discourse tester with maltParser and RegexpTagger

MaltParser looks like it was moved as well to nltk.parse.malt.MaltParser[[source]](https://www.nltk.org/_modules/nltk/parse/malt.html#MaltParser) I am not sure how we will proceed but if we were to update the example the maltparser would have...

Fringe cases in MT eval metrics

is this still open =?

confusing maxent formula.

status?

Translation Probabilities do not sum to 1 in IBM1 Translation Model

I might be wrong but I believe that the source words do not sum to one because they are not targets.

Incorrect documentation in nltk.stem.lancaster.LancasterStemmer class

I do not believe this is an issue with documentation, as the documentation matches the output of ran code. It appears to be an issue with the lancasterStemmer, if there...