Link paper and GitHub repository
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
| 3 |
library_name: transformers
|
|
|
|
|
|
|
|
|
|
| 4 |
pipeline_tag: text-classification
|
| 5 |
-
base_model: microsoft/deberta-v3-large
|
| 6 |
tags:
|
| 7 |
- citation-function-classification
|
| 8 |
- scholarly-positioning
|
| 9 |
- related-work-generation
|
| 10 |
- rwgbench
|
| 11 |
- multicite
|
| 12 |
-
datasets:
|
| 13 |
-
- multicite
|
| 14 |
-
metrics:
|
| 15 |
-
- f1
|
| 16 |
---
|
| 17 |
|
| 18 |
# RWGBench Citation Frame Classifier
|
|
@@ -22,6 +22,8 @@ Citation Frame Alignment (CFA). CFA evaluates whether a generated related work
|
|
| 22 |
section uses citations with a rhetorical frame distribution similar to the
|
| 23 |
author-written reference section.
|
| 24 |
|
|
|
|
|
|
|
| 25 |
The classifier is a DeBERTa-v3-large sequence-classification model fine-tuned
|
| 26 |
for multi-label citation-function prediction. It predicts seven
|
| 27 |
MultiCite-derived labels:
|
|
@@ -111,4 +113,4 @@ python src/evaluation/evaluate_generated_results.py \
|
|
| 111 |
```
|
| 112 |
|
| 113 |
RWGBench automatically marks numbered citations with `<cite>...</cite>` before
|
| 114 |
-
classification, matching the input format used during training.
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: microsoft/deberta-v3-large
|
| 3 |
+
datasets:
|
| 4 |
+
- multicite
|
| 5 |
library_name: transformers
|
| 6 |
+
license: mit
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
pipeline_tag: text-classification
|
|
|
|
| 10 |
tags:
|
| 11 |
- citation-function-classification
|
| 12 |
- scholarly-positioning
|
| 13 |
- related-work-generation
|
| 14 |
- rwgbench
|
| 15 |
- multicite
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# RWGBench Citation Frame Classifier
|
|
|
|
| 22 |
section uses citations with a rhetorical frame distribution similar to the
|
| 23 |
author-written reference section.
|
| 24 |
|
| 25 |
+
The model was introduced in the paper [RWGBench: Evaluating Scholarly Positioning in Related Work Generation](https://huggingface.co/papers/2606.24894). The official code repository is available at [BFTree/RWGBench](https://github.com/BFTree/RWGBench).
|
| 26 |
+
|
| 27 |
The classifier is a DeBERTa-v3-large sequence-classification model fine-tuned
|
| 28 |
for multi-label citation-function prediction. It predicts seven
|
| 29 |
MultiCite-derived labels:
|
|
|
|
| 113 |
```
|
| 114 |
|
| 115 |
RWGBench automatically marks numbered citations with `<cite>...</cite>` before
|
| 116 |
+
classification, matching the input format used during training.
|