|
--- |
|
language: |
|
- en |
|
thumbnail: https://cogcomp.seas.upenn.edu/images/logo.png |
|
tags: |
|
- text-classification |
|
- bart |
|
- xsum |
|
license: cc-by-sa-4.0 |
|
datasets: |
|
- xsum |
|
|
|
--- |
|
|
|
# bart-faithful-summary-detector |
|
|
|
## Model description |
|
|
|
A BART (base) model trained to classify whether a summary is *faithful* to the original article. See our [paper in NAACL'21](https://www.seas.upenn.edu/~sihaoc/static/pdf/CZSR21.pdf) for details. |
|
|
|
## Usage |
|
Concatenate a summary and a source document as input (note that the summary needs to be the **first** sentence). |
|
|
|
```python |
|
model = |
|
``` |
|
|
|
|
|
|
|
|
|
### BibTeX entry and citation info |
|
|
|
```bibtex |
|
@inproceedings{CZSR21, |
|
author = {Sihao Chen and Fan Zhang and Kazoo Sone and Dan Roth}, |
|
title = {{Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection}}, |
|
booktitle = {NAACL}, |
|
year = {2021} |
|
} |
|
``` |
