HPSG-Neural-Parser
HPSG-Neural-Parser copied to clipboard
DoodleJZ
Source code for "Head-Driven Phrase Structure Grammar Parsing on Penn Treebank" published at ACL 2019
Hi, I have followed distance-parser to preprocess the CTB data, but what are the exact steps for generating dependency trees (They only do constituency parsing)? Thank you!
Hey @DoodleJZ I came across this error while running your parser. Could please look into this and fix this ? Traceback (most recent call last): File "/content/drive/My Drive/Hd/DependencyParser/src_joint/main.py", line 746,...
I see that the POS predictions (produced by `parse.sh`) are all `UNK`s for the constituency output. Can the model generate POS tags?
Hello, I am trying to use your work to parse a raw sentence, but I can't find any sample input files showing the format of the sentence. Should I use...
I read the paper and try to run the codes. In paper 5, I find that the objective J_2(θ) for dependency parsing is totally nothing to do with the biaffine...
Loading model from models/joint_bert_dev=95.55_devuas=96.67_devlas=94.86.pt1... Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex. packages/torch/nn/_reduction.py:49: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead. warnings.warn(warning.format(ret)) Parsing sentences......
Firstly I would like to say that reading your paper was fascinating. Secondly I would like to thank you for advancing the state of the art on both constituency parsing...
Punctuation must be separated from words？This is inconvenient sentences： 1 no , it was n't black monday . 2 no , it was n't black monday. 3 no, it was...
Loading model from models/joint_bert_dev=95.55_devuas=96.67_devlas=94.86.pt... Reading dependency parsing data from data/ptb_test_3.3.0.sd Loading test trees from data/23.auto.clean... Loaded 2,416 test examples. Parsing test sentences... test-fscore (Recall=6.51, Precision=6.70, FScore=6.61) test-elapsed 0h00m34s best test...
Can you provide a sample of the command line to run the parser with the pre-trained models?
