Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,9 @@ language:
|
|
| 6 |
datasets:
|
| 7 |
- posmac
|
| 8 |
pipeline_tag: text2text-generation
|
|
|
|
|
|
|
|
|
|
| 9 |
tags:
|
| 10 |
- keywords-generation
|
| 11 |
- text-classifiation
|
|
@@ -41,7 +44,7 @@ The biggest advantage is the transferability of the vlT5 model, as it works well
|
|
| 41 |
- **Language model:** [t5-base](https://huggingface.co/t5-base)
|
| 42 |
- **Language:** pl, en (but works relatively well with others)
|
| 43 |
- **Training data:** POSMAC
|
| 44 |
-
- **Online Demo:** [https://nlp-demo-1.voicelab.ai/](https://nlp-demo-1.voicelab.ai/)
|
| 45 |
- **Paper:** [Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer, ACIIDS 2022](TBA)
|
| 46 |
|
| 47 |
# Corpus
|
|
|
|
| 6 |
datasets:
|
| 7 |
- posmac
|
| 8 |
pipeline_tag: text2text-generation
|
| 9 |
+
pipeline_kwargs:
|
| 10 |
+
- no_repeat_ngram_size=3
|
| 11 |
+
- num_beams=4
|
| 12 |
tags:
|
| 13 |
- keywords-generation
|
| 14 |
- text-classifiation
|
|
|
|
| 44 |
- **Language model:** [t5-base](https://huggingface.co/t5-base)
|
| 45 |
- **Language:** pl, en (but works relatively well with others)
|
| 46 |
- **Training data:** POSMAC
|
| 47 |
+
- **Online Demo:** Visit our online demo for better results [https://nlp-demo-1.voicelab.ai/](https://nlp-demo-1.voicelab.ai/)
|
| 48 |
- **Paper:** [Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer, ACIIDS 2022](TBA)
|
| 49 |
|
| 50 |
# Corpus
|