https://github.com/mikelewis0/easyccg

https://github.com/mikelewis0/easyccg

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/mikelewis0/easyccg
• Owner: mikelewis0
• License: mit
• Created: 2014-05-07T11:37:45.000Z (about 10 years ago)
• Default Branch: master
• Last Pushed: 2017-12-02T14:56:18.000Z (over 6 years ago)
• Last Synced: 2024-01-07T10:54:23.046Z (6 months ago)
• Language: Java
• Homepage: http://homepages.inf.ed.ac.uk/s1049478/easyccg.html
• Size: 58.7 MB
• Stars: 58
• Watchers: 13
• Forks: 19
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-nlg - EasyCCG - CCG: All combinators, common grammar format, parsing to logical form, parameter estimation for probabilistic CCG. (Grammar)

README

        
easyccg

=======

EasyCCG is a CCG parser created by Mike Lewis.

If you use EasyCCG in your research, please cite the following paper: A* CCG Parsing with a Supertag-factored Model, Mike Lewis and Mark Steedman, EMNLP 2014

Pre-trained models are available from: https://drive.google.com/#folders/0B7AY6PGZ8lc-NGVOcUFXNU5VWXc

To train new models, follow the instructions in training/README

Basic usage:

    java -jar easyccg.jar --model model

For N-best parsing:

    java -jar easyccg.jar --model model --nbest 10

To parse questions, use:

    java -jar easyccg.jar --model model_questions -s -r S[q] S[qem] S[wq]

If you want POS/NER tags in the output, you'll need to supply them in the input, using the format word|POS|NER. To get this format from the C&C tools, use the following:

    echo "parse me" | candc/bin/pos --model candc_models/pos | candc/bin/ner -model candc_models/ner -ofmt "%w|%p|%n \n" | java -jar easyccg.jar -model model_questions -i POSandNERtagged -o extended

To get Boxer-compatible Prolog output, use:

    echo "parse me" | candc/bin/pos --model candc_models/pos | candc/bin/ner -model candc_models/ner -ofmt "%w|%p|%n \n" | java -jar easyccg.jar -model model -i POSandNERtagged -o prolog -r S[dcl]