Age | Commit message (Expand) | Author |
2022-09-06 | Sort subfolders so that results are reproducible | John Bauer |
2022-09-06 | Import either lxml or ElementTree. ElementTree is slower, but doesn't requir... | John Bauer |
2022-09-06 | NAMESPACES -> NAMESPACE, replace all xpath with findall | John Bauer |
2022-09-06 | Mostly pl_ner conversion test - tests the conversion of the XML so far | John Bauer |
2022-09-06 | Separate out a smaller piece of the extraction function in convert_nkjp | John Bauer |
2022-09-04 | Replace click with argparse in the Polish NER, rather than adding a new libra... | John Bauer |
2022-09-04 | Remove global variable usage by passing it around everywhere instead | John Bauer |
2022-09-04 | NER Polish (#1110) | Karol Saputa |
2022-09-02 | Remove some unnecessary list creation. Rather than using shutil, read then w... | John Bauer |
2022-09-02 | Add some more notes on bilstm size experiments in the classifier | John Bauer |
2022-09-01 | Update compose_ete_results.py to allow multiple input files | John Bauer |
2022-09-01 | no enhanced dependencies | John Bauer |
2022-09-01 | Integrate the newer eval.py from udtools in place of the previously existing ... | John Bauer |
2022-09-01 | More informative errors if the data can't be found | John Bauer |
2022-09-01 | Update Hebrew default to a combined model | John Bauer |
2022-09-01 | Add the capacity to build he_combined models from UD_Hebrew-IAHLTwiki and a f...hebrew_combined | John Bauer |
2022-09-01 | Allow for a list of NER models in the processors argument, similar to the lis... | John Bauer |
2022-09-01 | Output the class chosen if choosing an xpos factory from scratch | John Bauer |
2022-09-01 | A couple more experiment notes | John Bauer |
2022-08-31 | Don't save optimizers for the non-checkpoints (and fix a save bug for the end... | John Bauer |
2022-08-31 | Make saved models smaller in the classifier test. Will hopefully save disk s... | John Bauer |
2022-08-31 | notes on the madgrad LR experiments | John Bauer |
2022-08-31 | Update a couple defaults based on recent experiments | John Bauer |
2022-08-31 | Save the best score when training a model so that future training from a chec... | John Bauer |
2022-08-31 | Update to 0.0005 - less likely to go completely bad | John Bauer |
2022-08-31 | Oops, correct a few uses of model in the classifier main program | John Bauer |
2022-08-31 | Save checkpoints with epochs_trained+1 at the end of an epoch (otherwise the ... | John Bauer |
2022-08-31 | Add a checkpoint mechanism to sentiment | John Bauer |
2022-08-31 | Simplify the load mechanism in classifier Trainer so that the load() call loa... | John Bauer |
2022-08-31 | Refactor a Trainer object out of the classifier.py main program. In addition...sentiment_trainer | John Bauer |
2022-08-31 | Refactor a bunch of data manipulation methods to data.py | John Bauer |
2022-08-31 | This should be a RuntimeError, not a generic Exception | John Bauer |
2022-08-31 | Refactor building an optimizer | John Bauer |
2022-08-31 | Move the loss function to the device w/o a call to cuda() | John Bauer |
2022-08-31 | Rearrange all classifier args to be part of classifier.py | John Bauer |
2022-08-31 | Refactor building the argparse for classifier | John Bauer |
2022-08-31 | recommend madgrad for default optimizer | John Bauer |
2022-08-30 | Add support for elmoformanylangs to sentiment | John Bauer |
2022-08-30 | More details log lines when saving a new best model in the classifier | John Bauer |
2022-08-30 | Add madgrad as an option, although none of the parameters have been CVed for ... | John Bauer |
2022-08-27 | move the HiNER dataset to under hindi/ | John Bauer |
2022-08-27 | log weighted F1, specifically for comparison to the HiNER dataset | John Bauer |
2022-08-27 | Add a weighted f1 to the confusion matrix calculations | John Bauer |
2022-08-27 | simple test of macro f1 result in confusion matrix | John Bauer |
2022-08-27 | Flesh out the errors a bit & add a line for '...' when we integrate the lates... | John Bauer |
2022-08-26 | Can bring the it_vit test back to life now that corenlp 4.5.0 is out | John Bauer |
2022-08-26 | Grad clipping in the constituency parser. Not a clear benefit yet, so just l... | John Bauer |
2022-08-26 | Restart training with the pieces inside a constituency model rather than usin... | John Bauer |
2022-08-26 | Fix run_ner.py after the earlier refactoring | John Bauer |
2022-08-25 | Oops, need to increment this line_idx as well | John Bauer |