Zheng Han comments

Results 8 comments of


                                            Zheng Han

Create another annotation at the same position without re-selecting span

> Ok, so let me describe in my words how I understand what you wish: > > * you create an annotation on L1 and assign some tag L1_t1 or...

Create another annotation at the same position without re-selecting span

> > Ok, so let me describe in my words how I understand what you wish: > > > > * you create an annotation on L1 and assign some...

Create another annotation at the same position without re-selecting span

My annotation task is to annotate the aspect/topic for layer L1 and annotate a sentiment for the same span in layer L2. As such, each span in a doc will...

Create another annotation at the same position without re-selecting span

@reckart yes but in my usecase of sentiment the number of aspect/topic is large, which multiplied by 5 (very_posotive/very_negative/positive/negative/neutral) is kind of cumbersome for the annotators to choose.

TPOTRegressor returns score of -inf when data increases

@JDRomano2 sorry for late response, GitHub muted notification somehow. The os I was running is an aws SageMaker instance of ml.m5.24xlarge which has 96 vCPUs and 384G memory. The file...

Failure with multiprocessing

Never mind. The code was still able to run and dump the model file despite the error. The error msg is annoying but doesn't seem to affect the result.

Batched IterableDataset

This issue is really smashing the selling point of HF datasets... The only workaround I've found so far is to create a customized IterableDataloader which improves the loading speed to...

NonParamDML always returns constant effect for continuous treatment

Hi @kbattocchi , I tried both `LinearDML` and `NonParamDML` with `PolynomialFeatures` as treatment_featurizer but they still output const ate values. Did I miss anything? ``` import numpy as np import...