Sentence Similarity
sentence-transformers
PyTorch
Transformers
English
roberta
feature-extraction
argument-mining
Twitter
Instructions to use TomatenMarc/WRAPresentations with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use TomatenMarc/WRAPresentations with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("TomatenMarc/WRAPresentations") sentences = [ "The formula: Not everyone who voted Leave is racist. But everyone who's racist voted Leave. Not everyone who voted Leave is thick. But everyone who's thick voted Leave. The thick racists therefore called the shots, whatever the thoughts of the minority of others. #thick #Brexit", "Men shouldn’t be making laws about women’s bodies #abortion #Texas", "Opinion: As the draconian (and then some) abortion law takes effecting #Texas, this is not an idle question for millions of Americans. A slippery slope towards more like-minded Republican state-legislatures to try to follow suit. #abortion #F24 HTTPURL", "’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU citizenship after #Brexit HTTPURL via @USER", "@USER Blah blah blah blah blah blah" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [5, 5] - Transformers
How to use TomatenMarc/WRAPresentations with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("TomatenMarc/WRAPresentations") model = AutoModel.from_pretrained("TomatenMarc/WRAPresentations") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,37 +13,67 @@ license: cc-by-sa-4.0
|
|
| 13 |
language:
|
| 14 |
- en
|
| 15 |
widget:
|
| 16 |
-
- source_sentence:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
sentences:
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
sentences:
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
sentences:
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
sentences:
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
---
|
| 48 |
|
| 49 |
# WRAPresentations -- A TACO-based Embedder For Inference and Information-Driven Argument Mining on Twitter
|
|
@@ -250,6 +280,27 @@ SentenceTransformer(
|
|
| 250 |
- **Compute Region:** [asia-southeast1](https://cloud.google.com/compute/docs/gpus/gpu-regions-zones?hl=en) (Singapore)
|
| 251 |
- **Carbon Emitted:** 0.21kg CO2
|
| 252 |
|
| 253 |
-
#
|
|
|
|
|
|
|
| 254 |
|
| 255 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
language:
|
| 14 |
- en
|
| 15 |
widget:
|
| 16 |
+
- source_sentence: >-
|
| 17 |
+
The formula: Not everyone who voted Leave is racist. But everyone who's
|
| 18 |
+
racist voted Leave. Not everyone who voted Leave is thick. But everyone
|
| 19 |
+
who's thick voted Leave. The thick racists therefore called the shots,
|
| 20 |
+
whatever the thoughts of the minority of others. #thick #Brexit
|
| 21 |
sentences:
|
| 22 |
+
- 'Men shouldn’t be making laws about women’s bodies #abortion #Texas'
|
| 23 |
+
- >-
|
| 24 |
+
Opinion: As the draconian (and then some) abortion law takes effecting
|
| 25 |
+
#Texas, this is not an idle question for millions of Americans. A slippery
|
| 26 |
+
slope towards more like-minded Republican state-legislatures to try to
|
| 27 |
+
follow suit. #abortion #F24 HTTPURL
|
| 28 |
+
- >-
|
| 29 |
+
’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU
|
| 30 |
+
citizenship after #Brexit HTTPURL via @USER
|
| 31 |
+
- '@USER Blah blah blah blah blah blah'
|
| 32 |
+
example_title: Reason
|
| 33 |
+
- source_sentence: This is NOT good for children.
|
| 34 |
sentences:
|
| 35 |
+
- 'Men shouldn’t be making laws about women’s bodies #abortion #Texas'
|
| 36 |
+
- >-
|
| 37 |
+
Opinion: As the draconian (and then some) abortion law takes effecting
|
| 38 |
+
#Texas, this is not an idle question for millions of Americans. A slippery
|
| 39 |
+
slope towards more like-minded Republican state-legislatures to try to
|
| 40 |
+
follow suit. #abortion #F24 HTTPURL
|
| 41 |
+
- >-
|
| 42 |
+
’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU
|
| 43 |
+
citizenship after #Brexit HTTPURL via @USER
|
| 44 |
+
- '@USER Blah blah blah blah blah blah'
|
| 45 |
+
example_title: Statement
|
| 46 |
+
- source_sentence: >-
|
| 47 |
+
Elon Musk ready with 'Plan B' if Twitter rejects his offer Read @USER Story
|
| 48 |
+
| HTTPURL #ElonMusk #ElonMuskTwitter #TwitterTakeover HTTPURL
|
| 49 |
sentences:
|
| 50 |
+
- 'Men shouldn’t be making laws about women’s bodies #abortion #Texas'
|
| 51 |
+
- >-
|
| 52 |
+
Opinion: As the draconian (and then some) abortion law takes effecting
|
| 53 |
+
#Texas, this is not an idle question for millions of Americans. A slippery
|
| 54 |
+
slope towards more like-minded Republican state-legislatures to try to
|
| 55 |
+
follow suit. #abortion #F24 HTTPURL
|
| 56 |
+
- >-
|
| 57 |
+
’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU
|
| 58 |
+
citizenship after #Brexit HTTPURL via @USER
|
| 59 |
+
- '@USER Blah blah blah blah blah blah'
|
| 60 |
+
example_title: Notification
|
| 61 |
+
- source_sentence: '@USER 👅is the Key 😂'
|
| 62 |
sentences:
|
| 63 |
+
- 'Men shouldn’t be making laws about women’s bodies #abortion #Texas'
|
| 64 |
+
- >-
|
| 65 |
+
Opinion: As the draconian (and then some) abortion law takes effecting
|
| 66 |
+
#Texas, this is not an idle question for millions of Americans. A slippery
|
| 67 |
+
slope towards more like-minded Republican state-legislatures to try to
|
| 68 |
+
follow suit. #abortion #F24 HTTPURL
|
| 69 |
+
- >-
|
| 70 |
+
’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU
|
| 71 |
+
citizenship after #Brexit HTTPURL via @USER
|
| 72 |
+
- '@USER Blah blah blah blah blah blah'
|
| 73 |
+
example_title: None
|
| 74 |
+
base_model:
|
| 75 |
+
- vinai/bertweet-base
|
| 76 |
+
library_name: sentence-transformers
|
| 77 |
---
|
| 78 |
|
| 79 |
# WRAPresentations -- A TACO-based Embedder For Inference and Information-Driven Argument Mining on Twitter
|
|
|
|
| 280 |
- **Compute Region:** [asia-southeast1](https://cloud.google.com/compute/docs/gpus/gpu-regions-zones?hl=en) (Singapore)
|
| 281 |
- **Carbon Emitted:** 0.21kg CO2
|
| 282 |
|
| 283 |
+
# Licensing
|
| 284 |
+
|
| 285 |
+
[WRAPresentations](https://huggingface.co/TomatenMarc/WRAPresentations) © 2023 is licensed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/?ref=chooser-v1).
|
| 286 |
|
| 287 |
+
# Citation
|
| 288 |
+
|
| 289 |
+
```
|
| 290 |
+
@inproceedings{feger-dietze-2024-bertweets,
|
| 291 |
+
title = "{BERT}weet{'}s {TACO} Fiesta: Contrasting Flavors On The Path Of Inference And Information-Driven Argument Mining On {T}witter",
|
| 292 |
+
author = "Feger, Marc and
|
| 293 |
+
Dietze, Stefan",
|
| 294 |
+
editor = "Duh, Kevin and
|
| 295 |
+
Gomez, Helena and
|
| 296 |
+
Bethard, Steven",
|
| 297 |
+
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
|
| 298 |
+
month = jun,
|
| 299 |
+
year = "2024",
|
| 300 |
+
address = "Mexico City, Mexico",
|
| 301 |
+
publisher = "Association for Computational Linguistics",
|
| 302 |
+
url = "https://aclanthology.org/2024.findings-naacl.146",
|
| 303 |
+
doi = "10.18653/v1/2024.findings-naacl.146",
|
| 304 |
+
pages = "2256--2266"
|
| 305 |
+
}
|
| 306 |
+
```
|