How to Custom Sentence Segmentation or Sentence Boundary Detection

Deep Learning Specialization on Coursera

A lot of NLP tools have sentence segmentation function, such as NLTK Sentence Segmentation, TextBlob Sentence Segmentation, Pattern Sentence Segmentation, spaCy Sentence Segmentation, but sometimes we need to custom the sentence segmentation or sentence boundary detection tool, how to do it? Following is a list I have found from google, just for reference:

https://groups.google.com/forum/#!topic/nltk-users/bxIEnmgeCSM
https://groups.google.com/forum/?fromgroups=#!topic/nltk-dev/y2zYJSOdevQ
http://wiki.apertium.org/wiki/Sentence_segmenting#NLTK_Punkt
https://github.com/nltk/nltk/issues/1824
https://stackoverflow.com/questions/35275001/use-of-punktsentencetokenizer-in-nltk
https://stackoverflow.com/questions/21160310/training-data-format-for-nltk-punkt
https://groups.google.com/forum/#!topic/nltk-users/bxIEnmgeCSM
https://stackoverflow.com/questions/14095971/how-to-tweak-the-nltk-sentence-tokenizer

Posted by TextProcessing


Leave a Reply

Your email address will not be published. Required fields are marked *