trendalytics / tl-attribution / issues / #9 - Tagging: Explore different tokenizers for punctuation — Bitbucket

Issue #9 resolved

Tomas Rojo Hernandez created an issue 2017-10-26

Currently using str.split() method, should try using other more advanced tokenizers like nltk's word_tokenize to solve punctuation issue. Related to #1

Comments (3)

Anton Kolechkin
- changed title to Tagging: Explore different tokenizers for punctuation
- edited description
- 2017-10-26T21:26:31+00:00
Anton Kolechkin
- changed status to resolved
- 2017-10-28T21:35:58+00:00
Anton Kolechkin
- assigned issue to
  
  Tomas Rojo Hernandez
- 2017-10-28T21:36:16+00:00
Log in to comment

Assignee: Tomas Rojo Hernandez

Type: enhancement

Priority: major

Status: resolved

Votes: 0

Watchers: 2