Travis Bartley
Travis Bartley
I've looked over the paper and am having a hard time sorting out the difference between phonological, featural, and inventory distances. To what I understand, phonological distances are simply those...
When running batch training with -d flag, the following error outputs: line 585, in main writer.writerow(['path']+nb_classes) NameError: name 'nb_classes' is not defined Looks like there is a misplaced variable assignment....
Wu and Coterrell's hard monotonic transduce.. Closes https://github.com/CUNY-CL/yoyodyne/issues/165. It builds off lstm module. To call you pass `hmm_lstm` for `--arch`. Hard monotonic constrain is enforced with `--enable_monotonic` while context window...
(Adding on issues board for documentation, this PR will be out over the week.) Wu and Cotterell's papers on strong alignment seem just up our alley for the library. There...
What are people's thoughts on adding preprocessing scripts to allow BPE-like tokenization of characters? Technically we already support this (just tokenize your input and use delineation function). But wonder if...
MIght as well set up an autoregressive decoder since T5 is on the docket. This shouldn't be too much of a hassle since the Transformer model works, but leaving as...
TorchMetrics support is pretty reliable nowadays and makes distributed training less annoying (no more World sizes, yay!). It also syncs well with Wandb logging and allows monitoring of training batch...
(Lowest of the low priorities) SSMs have been making the rounds but people have only cared about them for 'major' tasks. (NMT models, speech, LLM). Since they're special LSTMs and...
LightningCLI supports YAML configs. However we're going to need to add some additional OmegaConf and Hydra support to our existing scripts to best utilize this. This issue will work on...
For some reason, someone added an `embeddings` argument to `BaseModule` but didn't update the other modules to pass it. Why are we passing embeddings as an argument? Those should be...