davidjurgens / citation-function Goto Github PK

Hey!

Thanks for making this project public. I'm trying to run the pipeline mentioned in code/run-pipeline.sh but ran into some errors when executing run_topic_cv.py. The files required in lines 77-78 are unavailable in the repo or on the project webpage:

../working-dir/topics/citance.doc-topics.txt

Could you share the topics folder if available?

Further, if you have the trained model file on hand and an evaluation script, that would be of great help - I'm currently trying to evaluate the performance of this model.

glove.840B.300d.ARC-subset.txt is missing from the resources.
Line 76 of feature_extraction.py

Looking at citation-function/code/run-pipeline.sh, I understand some data should exist in these directories:

ARC_DIR=/shared/0/datasets/ACL-ARC/data/
AAN_DIR=/shared/0/datasets/ACL-AAN/aan/
ARC_JSON_DIR=/shared/0/datasets/ACL-ARC/json/

ARC_FTR_DIR=../working-dir/arc-ftrs/
FEATURE_VEC_DIR=../working-dir/feature-vecs/
CLASSIFIER_FILE=../working-dir/function-classifier.pkl

However, there is no description about what data should exist for each directories.
Could you add description?

I am interested in classifying citation-context and I have been trying to reproduce your work. However, I am struggling to generate 'arc-ftrs' files from convert_ARC_to_features.py file due to the requirement of large memory and memory leaks as well. Could you please kindly supply the data.
Thanks