Natural Language Parser

Seima Rao <seimarao@gmail.com>
Tue, 29 Sep 2015 06:15:22 +0530

          From comp.compilers

Related articles
Natural Language Parser seimarao@gmail.com (Seima Rao) (2015-09-29)
Re: Natural Language Parser gneuner2@comcast.net (George Neuner) (2015-09-29)
Re: Natural Language Parser thothic.quinn@gmail.com (Quinn Jackson) (2015-09-29)
Re: Natural Language Parser rpw3@rpw3.org (2015-09-30)
Re: unnatural natural language, was Natural Language Parser gneuner2@comcast.net (George Neuner) (2015-10-01)
Re: Natural Language Parser cr88192@hotmail.com (BGB) (2015-10-02)
Re: Natural Language Parser genew@telus.net (Gene Wirchenko) (2015-10-06)
| List of all articles for this month |

From: Seima Rao <seimarao@gmail.com>
Newsgroups: comp.compilers
Date: Tue, 29 Sep 2015 06:15:22 +0530
Organization: Compilers Central
Keywords: parse, question
Posted-Date: 29 Sep 2015 11:52:14 EDT

Hi,


        I am looking for a C++ API based English Language Parser.


        The specific task I want to do on a *regular basis* is to
        parse English Language Documents and arrive
        at a Mathematical artefact.


      The Mathematical artefact will (have) built a Syntax Tree
      of the English text that is input to the NLP parser.


      This is my only requirement. I dont need any semanticizing
        artefacts. So, my requirement is limited to parsing
      english language documents and arriving at a tree(
      or any other mathematical structure that binds the
      English grammar to the input document aka syntax trees).


      My guess is that the specific C++ API based NL parser
      will be using some english dictionary inside the tool
        to do all the jobs that are advertised.


        Can readers of this forum direct me to a stable and
        active C++ API based NL parser ?


        I have zero experience in natural language parsing(compiling)
        and zero experience in using such tools.


        However, I intend to maintain internally the source code
        of the toolkit via whatever version control software
      that is used by the developers of the tool so that
      I am able to get regular updates and not break
      anything.


Sincerely,
Seima Rao.
[You might start with this parser from Stanford:
http://nlp.stanford.edu/software/lex-parser.shtml
Or this one in python:
http://spacy.io/
Parsing English or any natural language is very hard, and you'll never
get more than an approximate result. Modern language translation
systems don't even try and use machine learning on large corpora.
-John]



Post a followup to this message

Return to the comp.compilers page.
Search the comp.compilers archives again.