jiangjiechen
commited on
Commit
•
c91e272
1
Parent(s):
d6b79a4
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
-
LOREN is an interpretable fact verification model trained on [FEVER](https://fever.ai), which aims to predict the veracity of a textual claim against a trustworthy knowledge source such as Wikipedia.
|
2 |
-
LOREN also decomposes the verification and makes accurate and faithful phrase-level veracity predictions without any phrasal veracity supervision.
|
3 |
|
4 |
-
This repo hosts the pre-trained
|
|
|
|
|
|
|
|
|
|
|
5 |
|
6 |
Please check out our AAAI 2022 paper for more details: "[LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification](https://arxiv.org/abs/2012.13577)".
|
|
|
1 |
+
`LOREN` is an interpretable fact verification model trained on [FEVER](https://fever.ai), which aims to predict the veracity of a textual claim against a trustworthy knowledge source such as Wikipedia.
|
2 |
+
`LOREN` also decomposes the verification and makes accurate and faithful phrase-level veracity predictions without any phrasal veracity supervision.
|
3 |
|
4 |
+
This repo hosts the following pre-trained models for `LOREN`:
|
5 |
+
- `fact_checking/`: the verification models based on BERT (large) and RoBERTa (large), respectively.
|
6 |
+
- `mrc_seq2seq/`: the generative machine reading comprehension model based on BART (base).
|
7 |
+
- `evidence_retrieval/`: the evidence sentence ranking models, which are copied directly from [KGAT](https://github.com/thunlp/KernelGAT).
|
8 |
+
|
9 |
+
More technical details can be found at [this GitHub Repo](https://github.com/jiangjiechen/LOREN).
|
10 |
|
11 |
Please check out our AAAI 2022 paper for more details: "[LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification](https://arxiv.org/abs/2012.13577)".
|