Analyzer's results

In response to the code mentioned in the preceding section, you will get all the supported Analyzer's results. This includes tokens, POS tags, and the Constituency Parsing tree:

  • Tokens: In the first step of analysis, linguistic will separate the sentences and tokens. The next task is to break the sentences into tokens. By default, in English, tokens are delimited by white space. In the first step, punctuation often should be split away from its surrounding context. Secondly, English has contractions, such as didn't or it's, where words have been compressed and abbreviated into smaller pieces. The goal of the tokenizer is to break the character sequence into words.
  • Parts-of-Speech Tags: After the separation of sentences ...

Get Building Bots with Microsoft Bot Framework now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.