Home

Awesome

SeqMix

The repository of our EMNLP'20 paper
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup
[paper] [slides]

Illustration of the three variants of SeqMix

Requirements

Install the required packages:

pip install -r requirements.txt

Key Parameters

Run

Active learning part

Random Sampling

python active_learn.py --active_policy=random

Least Confidence Sampling

python active_learn.py --active_policy=lc

Normalized Token Entropy sampling

python active_learn.py --active_policy=nte

Seqmix part

Whole sequence mixup

python active_learn.py --augment_method=soft

Sub-sequence mixup

python active_learn.py --augment_method=slack

Label-constrained sub-sequence mixup

python active_learn.py --augment_method=lf