mickeysjm / etypeclus Goto Github PK

How could I get the results reported in Table 4 of the paper? The output of the command "CUDA_VISIBLE_DEVICES=0 python3 latent_space_clustering.py
--dataset_path ./pandemic
--input_emb_name po_tuple_features_all_svos.pk" is only a file recording clustering results. Could you provide the codes to evaluate the results?????

Hi

I'm not sure if maybe i had a package version difference or something else, but to run the latest_space_clustering.py step I had to add "--input_dim1 716 --input_dim2 210" to the command as the prior commands appear to have produced embeddings with a different size to what it expected by default. Could you let us know if this was expected or not?

Note the README also points to pandemic for that step whereas all the proceeding steps given were using covid19.

Thanks

Tony

I run this command, it get this error.
how to solve it. thanks!!

i cannot find the paper "Corpus-based Open-Domain Event Type Induction"

Distinguished authors,
How could I connect the induced events with the sentences like Table 3 and 5 in your paper? I am a novice researcher in humanities, and I want to run your code to do some categorization based on the new corpus. The results are expected, but they are just clustered <p,o> pairs. How can I get the corresponding sentences?
Thanks.

1. When i run the command "python3 parse_corpus_and_extract_svo.py
   --is_sentence 1
   --input_file ./covid19/corpus.txt
   --save_path ./covid19/corpus_parsed_svo.pk",
   I see errors:

print(tok, tok.pos_, tok.dep_)
File "token.pyx", line 864, in spacy.tokens.token.Token.pos_.get
KeyError: 84

It seems that spacy has some bugs to get the pos of the word "false" when parsing the sentence "Institut Pasteur warns against false information circulating on social media". Could you give some suggestions?

2. How do I run the code on the ACE and ERE datasets??