sapienzanlp / esc Goto Github PK

Hi,

Thank you for the code! I wonder if there is something wrong when I am running the code: it is so slow, and one epoch consumed ~2h. I used the Tesla V100 server. But the paper reported only about 5 hours for training. Btw, I have to set the num_workers to 0 since when I increase that number larger than 1, then it has another error saying wordnet can't search for some keys (Idk why a key error could happen...)

Thank you!

Hi, I would like to ask how the F1 score of the noun，verb， adjective and adverb is obtained ？

Where the dataset-paths that you provide to the model must be in a format that follows the one introduced by Raganato et al. (2017). For reference, all the datasets in the directory data/WSD_Evaluation_Framework follow this format.

There is no folder WSD_Evaluation_Framework in data...
Any tool to automatically translate a sentence in the expected format? Or any example ?
@edobobo friendly ping

Hi on your readme you mentioned that

SemCor & Oxford (Available upon request, SE07: 77.8 | ALL: 81.5)

Where should I request it? Thanks!