Downloads · 30 days
0
loren
jiangjiechen/loren
loren is a machine learning model from jiangjiechen. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
LOREN is an interpretable fact verification model trained on FEVER, which aims to predict the veracity of a textual claim against a trustworthy knowledge source such as Wikipedia. LOREN also decomposes the verificatio…
Access
Public
Updated Dec 13, 2021
Repo size
4.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.8 GB · 90%
At a glance
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Dec 13, 2021
- SHA
- c91e272a
Model card
From the Hugging Face model README
LOREN is an interpretable fact verification model trained on FEVER, which aims to predict the veracity of a textual claim against a trustworthy knowledge source such as Wikipedia.
LOREN also decomposes the verification and makes accurate and faithful phrase-level veracity predictions without any phrasal veracity supervision.
This repo hosts the following pre-trained models for LOREN:
fact_checking/: the verification models based on BERT (large) and RoBERTa (large), respectively.mrc_seq2seq/: the generative machine reading comprehension model based on BART (base).evidence_retrieval/: the evidence sentence ranking models, which are copied directly from KGAT.
More technical details can be found at this GitHub Repo.
Please check out our AAAI 2022 paper for more details: "LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification".
- Created
- Mar 2, 2022
- Updated
- Dec 13, 2021