W3C home > Mailing lists > Public > semantic-web@w3.org > November 2019

Re: From PSG to OWL

From: Christian Chiarcos <christian.chiarcos@web.de>
Date: Fri, 22 Nov 2019 11:45:55 +0100
Message-ID: <CAC1YGdgJEjMWQ2vR4Oc-gXJh1DD0wZUHb5y2vvfoYTXZXmLMng@mail.gmail.com>
To: Mikael Pesonen <mikael.pesonen@lingsoft.fi>
Cc: SW-forum <semantic-web@w3.org>
Hi,

We just extended CoNLL-RDF for PennTreebank-style and XML-based tree
annotations in TSV formats (https://github.com/acoli-repo/conll-rdf, see
examples/tree-example.sh and examples/xml-example.sh). This is handy if
your annotations come in a (any) TSV format (as most NLP tools support).
If you look for plain converters for other formats and without much
ontological foundation, you can take a look into
https://github.com/acoli-repo/LLODifier for various formats, e.g., TIGER,
PTB, Xigt, TEI.
If you ask for more high-level information extraction pipelines, Aldo
mentioned FRED, already, and you might also want to take a look into NIF (
https://persistence.uni-leipzig.org/nlp2rdf/, supports phrases, but no
empty elements such as traces) and the LAPPS Grid (
http://vocab.lappsgrid.org/).
As a vocabulary for representing phrase structures, I personally prefer
POWLA (http://purl.org/powla) for representing the structure of annotations
-- because we designed it to be small and generic --, and OLiA (
http://purl.org/olia/) as an ontology for representing the actual
annotations.

Best,
Christian


Am Do., 21. Nov. 2019 um 16:52 Uhr schrieb Mikael Pesonen <
mikael.pesonen@lingsoft.fi>:

> Hi,
>
> given phrase structure grammars of some text, are there any theories,
> work or utilities done for extracting knowledge from them into semantic
> (OWL) form?
> There are lots of steps involved, for example identifying the entities
> and relations between entities.
>
> Br
>
>
Received on Friday, 22 November 2019 10:46:10 UTC

This archive was generated by hypermail 2.4.0 : Friday, 17 January 2020 19:51:39 UTC