Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: text2text-generation
|
6 |
+
---
|
7 |
+
# Model Card for Model ID
|
8 |
+
|
9 |
+
## Model Details
|
10 |
+
|
11 |
+
### Model Description
|
12 |
+
|
13 |
+
- **Model type:** Text-to-Text Generation
|
14 |
+
- **Language(s) (NLP):** English
|
15 |
+
- **License:** MIT License
|
16 |
+
- **Finetuned from model:** T5 Base Model (Google AI)
|
17 |
+
|
18 |
+
## Uses
|
19 |
+
|
20 |
+
The News2Topic T5-base model is designed for automatic generation of topic names from news articles or news-like text. It can be integrated into news aggregation platforms, content management systems, or used for enhancing news browsing and searching experiences by providing concise topics.
|
21 |
+
|
22 |
+
## How to Get Started with the Model
|
23 |
+
|
24 |
+
```
|
25 |
+
from transformers import pipeline
|
26 |
+
|
27 |
+
pipe = pipeline("text2text-generation", model="textgain/News2Topic-T5-base")
|
28 |
+
|
29 |
+
```
|
30 |
+
# Example usage
|
31 |
+
|
32 |
+
```
|
33 |
+
news_text = "Your news text here."
|
34 |
+
print(pipe(news_text))
|
35 |
+
```
|
36 |
+
|
37 |
+
## Training Details
|
38 |
+
|
39 |
+
### Training Data
|
40 |
+
|
41 |
+
The News2Topic T5-base model was trained on a 21K sample of the "newsroom" dataset annotated with synthetic data generated by GPT-3.5-turbo
|
42 |
+
|
43 |
+
### Training Procedure
|
44 |
+
|
45 |
+
The model was trained for 3 epochs, with a learning rate of 0.00001, a maximum sequence length of 512, and a training batch size of 12.
|
46 |
+
|
47 |
+
## Citation
|
48 |
+
|
49 |
+
**BibTeX:**
|
50 |
+
```
|
51 |
+
@article{Kosar_De Pauw_Daelemans_2024,
|
52 |
+
title={Comparative Evaluation of Topic Detection: Humans vs. LLMs}, volume={13},
|
53 |
+
url={https://www.clinjournal.org/clinj/article/view/173}, journal={Computational Linguistics in the Netherlands Journal},
|
54 |
+
author={Kosar, Andriy and De Pauw, Guy and Daelemans, Walter},
|
55 |
+
year={2024},
|
56 |
+
month={Mar.},
|
57 |
+
pages={91–120} }
|
58 |
+
```
|