Could we add our own abbreviations for the sentence boundary detection?

winkjs / wink-nlp-utils

NLP Functions for amplifying negations, managing elisions, creating ngrams, stems, phonetic codes to tokens and more.

http://winkjs.org/wink-nlp-utils/

MIT License

123 stars 12 forks source link

Could we add our own abbreviations for the sentence boundary detection? #30

Closed chrislim closed 2 years ago

chrislim commented 3 years ago

The current list of abbreviations in the sentence boundary detection code is quite limited. Could we have the option of passing in other abbreviations to be considered so that we do not have sentences broken up in incorrect places?

sanjayaksaxena commented 3 years ago

Hello @chrislim

Right now such capability does not exist. But we can surely explore that.

In the meantime, you may like to explore wink-nlp — our main NLP package. Its comprehensive documentation is available at https://winkjs.org/wink-nlp/getting-started.html.