coref

coref copied to clipboard

Hi @mandarjoshi90 , Thanks for your work. I am trying to visualize Spanbert base attention weights. when I read through the code couldn't find any param to get them. Could...

prasad4fun

Model structure redundancy

2

Hi, The span width embedding over here: https://github.com/mandarjoshi90/coref/blob/bd04f2e19b9dcc0b8bba848a335e4af3be50741c/independent.py#L379 is pretty much equivalent to the span embedding over there, since the width embedding is concatenated to other span embeddings and then...

grig-guz

undefined symbol: _ZN10tensorflow12OpDefBuilder4AttrESs

1

Hello Please after setup all the requirements , I want now to do a setup for training by running this command `./setup_training.sh $data_dir` but i am getting this error "...

TatianaMoteuN

Code to go from clusters to transformed document

2

Is there code to go from "The dog wagged its tail" --> "The dog wagged the dog's tail"? Basically, go from clusters to head prediction and then replacement of mentions...

griff4692

The loss will increase after reducing to about 10

1

I train the model on Ontonotes5.0 chinese dataset, at first it works fine with constantly decreasing loss, but after 30 epoches, the loss will increase after reducing to about 10....

viviqi

All the links won't open, is the server crashed

liyaoshigehaoren

Increase version of MarkupSafe

1

Version 1.0 of MarkupSafe fails to build with the latest version of setuptools (see https://github.com/pallets/markupsafe/issues/116). Shifting to 1.1.1 doesn't seem to break the code and resolves this build issue.

jkkummerfeld

justiceo

Questions on Table 2 of Bert paper

5

1. Table 2 shows many systems results on GAP, could I ask it is on GAP dev dataset or test dataset? 2. I couldn't reproduce c2f_coref result now, not sure...

HaixiaChai

Is there a bug in batch_gather?

2

in independent.py `top_fast_antecedent_scores = util.batch_gather(fast_antecedent_scores, top_antecedents) # [k, c]` sometimes return `[NaN, NaN ...]` I tried to print the value of tensors using `tf.Print()` `batch_gather in util.py` ``` def batch_gather(txt,...

fairy-of-9