search

IBM / transition-amr-parser

SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.
Apache License 2.0
246 stars 48 forks source link

fix amr2joint config name typo in README #34

Closed xsthunder closed 2 years ago

xsthunder commented 2 years ago

Thank you for releasing your code and checkpoints! It's very helpful. However, there may be a config name typo in the Trained checkpoints section in README.md. recreating #33 for sign off problem.

fix typo

existing problems

The config is the same for those two lines: 

amr3joint_ontowiki2_g2g-structured-bart-large | 10 | 85.9 |
amr3joint_ontowiki2_g2g-structured-bart-large | 10 | 84.4 |

possible fix

Change the word in the first line from amr3joint to amr2joint, according to your aws bucket and paper. 

amr2joint_ontowiki2_g2g-structured-bart-large | 10 | 85.9 |
amr3joint_ontowiki2_g2g-structured-bart-large | 10 | 84.4 |

Best wishes!

Signed-off-by: xsthunder xsthunder@outlook.com

ramon-astudillo commented 2 years ago

This was a typo, thanks!