search

LexPredict / lexpredict-lexnlp

LexNLP by LexPredict
GNU Affero General Public License v3.0
698 stars 178 forks source link

Doc or Sample request for Segmentation #47

Open danactive opened 4 years ago

danactive commented 4 years ago

I'm test driving your NLP, and I'm interested in segment recognition of Paragraphs. I see you stubbed your docs Segmentation and related methods for real-world text. May I nudge you to produce a code sample? How should I detect 1.2.2.2 is "Subparagraph 2 of Section one subsection 2 paragraph 2"?

My scenario is text of bulleted lists

1 (1) Section one subsection 1
    (2) Section one subsection 2
        (a) Paragraph 1 of Section one subsection 2
        (b) Paragraph 2 of Section one subsection 2
            (i) Subparagraph 1 of Section one subsection 2 paragraph 2
            (ii) Subparagraph 2 of Section one subsection 2 paragraph 2
        (c) Paragraph 3 of Section one subsection 2
    (3) Section one subsection 3
2 (1) Section two subsection 1