Cristina Garbacea

Results 9 comments of Cristina Garbacea

Corpus Bleu evaluation when number of references and hypothesis are large and code runs out of memory

Thanks a lot for your reply. I have indeed tried to replicate the 170k sentences 5k times and pass that to compute_metrics, however on a 504 GB RAM machine my...

An error training an Encoder-Decoder Attention Model

Hi @qiang2100 ! I am encountering the same error, did you find what is causing it?

How to sample from the pre-trained model?

When running the command: python model/test.py -test_ckpt text_simplification/pretrained_model/ckpt I get the error below: Traceback (most recent call last): File "model/test.py", line 341, in test(config, ckpt) File "model/test.py", line 43, in...

is it possible to use this model on general sentences?

Hi @kasra-pak , I am interested in doing the same. Did you receive an answer to your question?

how to GET the BOXER OUTPUT (XML format) ??

Is Boxer v1.00 available for download? If yes, where can I get it from? Thanks!

First time deploy instructions

I am using the same commands posted above to retrieve the xml output from Boxer 1.00, however I am getting errors: bin/candc --input test.txt --models models/boxer > test.ccg this file...

Where is Boxer v1.00?

Is Boxer v1.00 available for download? If yes, where can I get it from? Thanks!

Round-trip encoding of tokens [!] failed, Warning: lexer error: too many states: 10406 >= 10000; stopping

HI @Harsha-Nori , thanks a lot for your answer! I have installed guidance --pre using pip and the version installed is 0.2.0rc1. I am using this in combination with publicly...

Round-trip encoding of tokens [!] failed, Warning: lexer error: too many states: 10406 >= 10000; stopping

@Harsha-Nori Any thoughts? Sorry to ask again, it's a pressing issue.