A Dataset for Identifying Question-Answer Pairs in Video Transcripts
To run the rule-based model, use the following commands:
cd code/rule
python rule.py
To run the BERT-based model, use the following commands:
cd code/tranformer
bash my_run.sh
The dataset provided in this repo is licensed under CC BY-NC 4.0 international license.
If you use the dataset released in this repo, please cite our paper:
@inproceedings{veyseh-et-al-2022-behanceqa,
title={{BehanceQA: A New Dataset for Identifying Question-Answer Pairs in Video Transcripts}},
author={Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt and Thien Huu Nguyen},
year={2022},
booktitle={Proceedings of LREC},
}