|
--- |
|
|
|
language: en |
|
|
|
license: apache-2.0 |
|
|
|
--- |
|
|
|
|
|
# QAmden: Question-Answering-based Multi-DocumENt model |
|
|
|
HF-version of the QAmden model: Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering (ACL 2023). |
|
|
|
|
|
You can use it by |
|
|
|
```python |
|
from transformers import ( |
|
AutoTokenizer, |
|
LEDConfig, |
|
LEDForConditionalGeneration, |
|
) |
|
# load model and tokenizer |
|
tokenizer = AutoTokenizer.from_pretrained('biu-nlp/QAmden') |
|
config=LEDConfig.from_pretrained('biu-nlp/QAmden') |
|
|
|
model = LEDForConditionalGeneration.from_pretrained('biu-nlp/QAmden') |
|
``` |
|
|
|
The original repo is [here](https://github.com/aviclu/peekacross). |
|
|
|
If you find our work useful, please cite the paper as: |
|
|
|
```python |
|
@article{caciularu2023peekacross, |
|
title={Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering}, |
|
author={Caciularu, Avi and Peters, Matthew E and Goldberger, Jacob and Dagan, Ido and Cohan, Arman}, |
|
journal={The 61st Annual Meeting of the Association for Computational Linguistics: ACL 2023}, |
|
year={2023} |
|
} |
|
``` |
|
|
