Adding tweeteval classifier
This commit is contained in:
parent
c6eb303fb1
commit
c3f00119f3
|
@ -0,0 +1,70 @@
|
|||
# Twitter-roBERTa-base
|
||||
|
||||
This is a roBERTa-base model trained on ~58M tweets and finetuned for the Sentiment Analysis task at Semeval 2018.
|
||||
For full description: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf).
|
||||
To evaluate this and other models on Twitter-specific data, please refer to the [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
|
||||
|
||||
## Example of classification
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForSequenceClassification
|
||||
from transformers import TFAutoModelForSequenceClassification
|
||||
from transformers import AutoTokenizer
|
||||
import numpy as np
|
||||
from scipy.special import softmax
|
||||
import csv
|
||||
import urllib.request
|
||||
|
||||
# Tasks:
|
||||
# emoji, emotion, hate, irony, offensive, sentiment
|
||||
# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
|
||||
|
||||
task='sentiment'
|
||||
MODEL = f"cardiffnlp/twitter-roberta-base-{task}"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(MODEL)
|
||||
|
||||
# download label mapping
|
||||
labels=[]
|
||||
mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt"
|
||||
with urllib.request.urlopen(mapping_link) as f:
|
||||
html = f.read().decode('utf-8').split("\n")
|
||||
spamreader = csv.reader(html[:-1], delimiter='\t')
|
||||
labels = [row[1] for row in spamreader]
|
||||
|
||||
# PT
|
||||
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
|
||||
model.save_pretrained(MODEL)
|
||||
|
||||
text = "Good night 😊"
|
||||
encoded_input = tokenizer(text, return_tensors='pt')
|
||||
output = model(**encoded_input)
|
||||
scores = output[0][0].detach().numpy()
|
||||
scores = softmax(scores)
|
||||
|
||||
# # TF
|
||||
# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)
|
||||
# model.save_pretrained(MODEL)
|
||||
|
||||
# text = "Good night 😊"
|
||||
# encoded_input = tokenizer(text, return_tensors='tf')
|
||||
# output = model(encoded_input)
|
||||
# scores = output[0][0].numpy()
|
||||
# scores = softmax(scores)
|
||||
|
||||
ranking = np.argsort(scores)
|
||||
ranking = ranking[::-1]
|
||||
for i in range(scores.shape[0]):
|
||||
l = labels[ranking[i]]
|
||||
s = scores[ranking[i]]
|
||||
print(f"{i+1}) {l} {np.round(float(s), 4)}")
|
||||
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
1) positive 0.8466
|
||||
2) neutral 0.1458
|
||||
3) negative 0.0076
|
||||
```
|
|
@ -0,0 +1,70 @@
|
|||
# Twitter-roBERTa-base
|
||||
|
||||
This is a roBERTa-base model trained on ~58M tweets and finetuned for the Sentiment Analysis task at Semeval 2018.
|
||||
For full description: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf).
|
||||
To evaluate this and other models on Twitter-specific data, please refer to the [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
|
||||
|
||||
## Example of classification
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForSequenceClassification
|
||||
from transformers import TFAutoModelForSequenceClassification
|
||||
from transformers import AutoTokenizer
|
||||
import numpy as np
|
||||
from scipy.special import softmax
|
||||
import csv
|
||||
import urllib.request
|
||||
|
||||
# Tasks:
|
||||
# emoji, emotion, hate, irony, offensive, sentiment
|
||||
# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
|
||||
|
||||
task='sentiment'
|
||||
MODEL = f"cardiffnlp/twitter-roberta-base-{task}"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(MODEL)
|
||||
|
||||
# download label mapping
|
||||
labels=[]
|
||||
mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt"
|
||||
with urllib.request.urlopen(mapping_link) as f:
|
||||
html = f.read().decode('utf-8').split("\n")
|
||||
spamreader = csv.reader(html[:-1], delimiter='\t')
|
||||
labels = [row[1] for row in spamreader]
|
||||
|
||||
# PT
|
||||
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
|
||||
model.save_pretrained(MODEL)
|
||||
|
||||
text = "Good night 😊"
|
||||
encoded_input = tokenizer(text, return_tensors='pt')
|
||||
output = model(**encoded_input)
|
||||
scores = output[0][0].detach().numpy()
|
||||
scores = softmax(scores)
|
||||
|
||||
# # TF
|
||||
# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)
|
||||
# model.save_pretrained(MODEL)
|
||||
|
||||
# text = "Good night 😊"
|
||||
# encoded_input = tokenizer(text, return_tensors='tf')
|
||||
# output = model(encoded_input)
|
||||
# scores = output[0][0].numpy()
|
||||
# scores = softmax(scores)
|
||||
|
||||
ranking = np.argsort(scores)
|
||||
ranking = ranking[::-1]
|
||||
for i in range(scores.shape[0]):
|
||||
l = labels[ranking[i]]
|
||||
s = scores[ranking[i]]
|
||||
print(f"{i+1}) {l} {np.round(float(s), 4)}")
|
||||
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
1) positive 0.8466
|
||||
2) neutral 0.1458
|
||||
3) negative 0.0076
|
||||
```
|
|
@ -0,0 +1,33 @@
|
|||
{
|
||||
"_name_or_path": "tweeteval_new/roberta-base-rt-sentiment/",
|
||||
"architectures": [
|
||||
"RobertaForSequenceClassification"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.1,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 2,
|
||||
"gradient_checkpointing": false,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"hidden_size": 768,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1",
|
||||
"2": "LABEL_2"
|
||||
},
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1,
|
||||
"LABEL_2": 2
|
||||
},
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 514,
|
||||
"model_type": "roberta",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 12,
|
||||
"pad_token_id": 1,
|
||||
"type_vocab_size": 1,
|
||||
"vocab_size": 50265
|
||||
}
|
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
@ -0,0 +1 @@
|
|||
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
Binary file not shown.
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue