https://github.com/cogcomp/pabi
https://github.com/cogcomp/pabi
Last synced: 6 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/cogcomp/pabi
- Owner: CogComp
- Created: 2021-09-10T00:01:07.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-09-13T22:10:52.000Z (over 4 years ago)
- Last Synced: 2023-09-29T20:32:38.438Z (over 2 years ago)
- Language: Python
- Size: 39.1 KB
- Stars: 1
- Watchers: 6
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# PABI
This is the code repository for the EMNLP paper [Foreseeing the Benefits of Incidental Supervision](https://cogcomp.seas.upenn.edu/page/publication_view/959).
If you use this code for your work, please cite
```
@inproceedings{HZNR21,
author = {Hangfeng He and Mingyuan Zhang and Qiang Ning and Dan Roth},
title = {{Foreseeing the Benefits of Incidental Supervision}},
booktitle = {Proc. of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
year = {2021},
url = "https://cogcomp.seas.upenn.edu/papers/HZNR21.pdf",
funding = {LwLL, MURI, CwC},
}
```
## Installing Dependencies
Use virtual environment tools (e.g miniconda) to install packages and run experiments\
python>=3.6\
pip install -r requirements.txt
## Code Organization
The code is organized as follows:
- bpp.py (CWBPP algorithm for learning with various inductive signals)
- run_ner.py (BERT for NER)
- run_squad.py (BERT for QA)
## Reproducing experiments
To reproduce the experiments for learning with various inductive signals:
```
sh run_experiments.sh
```
To reproduce the experiments for cross-domain signals:
```
sh run_xdomain_ner_experiments.sh
sh run_xdomain_qa_experiments.sh
```