Go to file
2019-02-28 10:15:14 +01:00
bilateral-srl@86642e1866 added some data and updated README.md 2019-01-29 07:55:13 +01:00
data fixed paths 2019-02-27 17:32:19 +01:00
dockerfiles some changes on server 2019-02-28 09:40:25 +01:00
parser some changes on server 2019-02-28 09:40:25 +01:00
tools added logger 2019-02-28 10:15:14 +01:00
.gitignore some changes on server 2019-02-28 09:40:25 +01:00
.gitmodules added some data and updated README.md 2019-01-29 07:55:13 +01:00
data_format.xml msdmap.py 2019-02-10 23:23:24 +01:00
Makefile ready to go 2019-02-28 08:20:21 +01:00
README.md ready to go 2019-02-28 08:20:21 +01:00

cjvt-srl-tagging

We'll be using mate-tools to perform SRL on Kres.

workspace

The tools require Java. Go to ./dockerfiles/python-java/ and run make.
You should get a docker environment, mounting this repo.

mate-tools

Check out ./tools/srl-20131216/README.md.

Scripts

Check all possible xml tags (that occur after the tag.

cat F0006347.xml.parsed.xml | grep -A 999999999999 -e '<body>' | grep -o -e '<[^" "]*' | sort | uniq

Tools

  • Parser for reading both SSJ500k 2.1 TEI xml and Kres F....xml.parsed.xml" files found in ./tools/parser/parser.py.
  • fillpred_model for creating a yes/no model for preditcing the predicate (based on ssj500k data).

Usage

$ cd ./dockerfiles/python-java`
$ make
# you should be inside a container now
$ cd ./cjvt-srl-tagging
$ make

If you want to run it on a server overnight, you might want to use nohup, so you can close the ssh connection without closing the process.

$ nohup make > tagging.log &

Makefile

The Makefile follows certain steps:

  1. Create a fillpred model.
  2. Parse .xml files and create .tsv files.
  3. Run mate-tools srl-tagger on the created .tsv files.

Sources