cjvt-srl-tagging/README.md

32 lines
952 B
Markdown
Raw Normal View History

2019-01-25 06:06:40 +00:00
# cjvt-srl-tagging
2019-01-29 06:55:13 +00:00
We'll be using mate-tools to perform SRL on Kres.
## workspace
The tools require Java.
2019-02-14 07:18:06 +00:00
See `./dockerfiles/python-java/README.md` for environment preparation.
2019-01-25 06:29:52 +00:00
## mate-tools
2019-02-03 21:54:26 +00:00
Check out `./tools/srl-20131216/README.md`.
2019-01-29 06:55:13 +00:00
2019-02-03 21:54:26 +00:00
## Scripts
Check all possible xml tags (that occur after the <body> tag.
'cat F0006347.xml.parsed.xml | grep -A 999999999999 -e '<body>' | grep -o -e '<[^" "]*' | sort | uniq'
2019-01-29 06:55:13 +00:00
2019-02-03 21:54:26 +00:00
## Tools
* Parser for reading both `SSJ500k 2.1 TEI xml` and `Kres F....xml.parsed.xml"` files found in `./tools/parser/parser.py`.
2019-01-29 06:55:13 +00:00
## Usage
```bash
$ ./dockerfiles/python-java`
$ make
# you should be inside a container now
$ make <option>
```
2019-01-25 06:29:52 +00:00
## Sources
2019-01-29 06:56:37 +00:00
* [1] (mate-tools) https://code.google.com/archive/p/mate-tools/
* [2] (benchmarking) https://github.com/clarinsi/bilateral-srl
2019-02-02 19:45:35 +00:00
* [3] (conll 2008 paper) http://www.aclweb.org/anthology/W08-2121.pdf
2019-02-03 21:54:26 +00:00
* [4] (format CoNLL 2009) https://wiki.ufal.ms.mff.cuni.cz/format-conll