英文:
How to generate sentiment scores using predefined aspects with deberta-v3-base-absa-v1.1 Huggingface model?
问题
- 使用预定义的方面来生成情感分数
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import pandas as pd
# 加载ABSA模型和分词器
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
# 生成方面和情感
aspects = []
sentiments = []
for index, row in df.iterrows():
text = row['text']
row_aspects = row['aspects']
aspect_sentiments = []
for aspect in row_aspects:
inputs = tokenizer(text, aspect, return_tensors="pt")
with torch.inference_mode():
outputs = model(**inputs)
predicted_sentiment = torch.argmax(outputs.logits).item()
sentiment_label = model.config.id2label[predicted_sentiment]
aspect_sentiments.append(f"{aspect}: {sentiment_label}")
aspects.append(row_aspects)
sentiments.append(aspect_sentiments)
# 将生成的方面和情感添加到DataFrame中
df['generated_aspects'] = aspects
df['generated_sentiments'] = sentiments
# 打印更新后的DataFrame
print(df)
- 生成文本的方面和相应的情感分数
import torch
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
aspects = ["food", "service"]
text = "The food was great but the service was terrible."
sentiment_aspect = {}
for aspect in aspects:
inputs = tokenizer(text, aspect, return_tensors="pt")
with torch.inference_mode():
outputs = model(**inputs)
scores = F.softmax(outputs.logits[0], dim=-1)
label_id = torch.argmax(scores).item()
sentiment_aspect[aspect] = (model.config.id2label[label_id], scores[label_id].item())
print(sentiment_aspect)
英文:
I have a dataframe , where there is text in 1st column and predefine aspect in another column however there is no aspects defined for few text ,for example row 2.
data = {
'text': [
"The camera quality of this phone is amazing.",
"The belt is poor quality",
"The battery life could be improved.",
"The display is sharp and vibrant.",
"The customer service was disappointing."
],
'aspects': [
["camera", "phone"],
[],
["battery", "life"],
["display"],
["customer service"]
]
}
df = pd.DataFrame(data)
I want to generate two things
- using pre define aspect for the text, generate sentiment score
- using text generate aspect and also the sentiment score from the package
Note: This package yangheng/deberta-v3-base-absa-v1.1
1)generate sentiment score based on predefine aspects
2)generate both aspect and it's respective sentiments
Note Row 2 does not have predefine aspect
I tried and getting error
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import pandas as pd
# Load the ABSA model and tokenizer
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
# Generate aspects and sentiments
aspects = []
sentiments = []
for index, row in df.iterrows():
text = row['text']
row_aspects = row['aspects']
aspect_sentiments = []
for aspect in row_aspects:
inputs = tokenizer(text, aspect, return_tensors="pt")
with torch.inference_mode():
outputs = model(**inputs)
predicted_sentiment = torch.argmax(outputs.logits).item()
sentiment_label = model.config.id2label[predicted_sentiment]
aspect_sentiments.append(f"{aspect}: {sentiment_label}")
aspects.append(row_aspects)
sentiments.append(aspect_sentiments)
# Add the generated aspects and sentiments to the DataFrame
df['generated_aspects'] = aspects
df['generated_sentiments'] = sentiments
# Print the updated DataFrame
print(df)
generic example to use the package
import torch
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
aspects = ["food", "service"]
text = "The food was great but the service was terrible."
sentiment_aspect = {}
for aspect in aspects:
inputs = tokenizer(text, aspect, return_tensors="pt")
with torch.inference_mode():
outputs = model(**inputs)
scores = F.softmax(outputs.logits[0], dim=-1)
label_id = torch.argmax(scores).item()
sentiment_aspect[aspect] = (model.config.id2label[label_id], scores[label_id].item())
print(sentiment_aspect)
Desired Output
答案1
得分: 2
# Load the ABSA model and tokenizer
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
for aspect in ['camera', 'phone']:
print(aspect, classifier('The camera quality of this phone is amazing.', text_pair=aspect))
[out]:
camera [{'label': 'Positive', 'score': 0.9967294931411743}]
phone [{'label': 'Neutral', 'score': 0.9472787380218506}]
To get the zero-shot classification scores in general, try using pipeline
:
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from transformers import pipeline
# Load the ABSA model and tokenizer
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
pipe = pipeline("zero-shot-classification", model=model, tokenizer=tokenizer)
pipe("The camera quality of this phone is amazing.", candidate_labels=["camera", "phone"])
[out]:
{'sequence': 'The camera quality of this phone is amazing.',
'labels': ['camera', 'phone'],
'scores': [0.9036691784858704, 0.09633082151412964]}
Depending on what "text generated aspect" means, perhaps it's keyword extraction, and if so, doing a search on https://huggingface.co/models?search=keyword, gives this as the top downloaded model, https://huggingface.co/yanekyuk/bert-uncased-keyword-extractor
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer2 = AutoTokenizer.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
model2 = AutoModelForTokenClassification.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
def extract_aspect(text):
extractor = pipeline("ner", model=model2, tokenizer=tokenizer2)
phrasesids = []
for tag in extractor(text):
if tag['entity'].startswith('B'):
phrasesids.append([tag['start'], tag['end']])
if tag['entity'].startswith('I'):
phrasesids[-1][-1] = tag['end']
phrases = [text:p[1]] for p in phrasesids]
return phrases
text = "The camera quality of this phone is amazing."
extract_aspect(text)
[out]:
camera
Putting the extractor and classifier together:
from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
from transformers import pipeline
# Load the ABSA model and tokenizer
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
classifier = pipeline("zero-shot-classification", model=model, tokenizer=tokenizer)
tokenizer2 = AutoTokenizer.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
model2 = AutoModelForTokenClassification.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
def extract_aspect(text):
extractor = pipeline("ner", model=model2, tokenizer=tokenizer2)
phrasesids = []
for tag in extractor(text):
if tag['entity'].startswith('B'):
phrasesids.append([tag['start'], tag['end']])
if tag['entity'].startswith('I'):
phrasesids[-1][-1] = tag['end']
phrases = [text:p[1]] for p in phrasesids]
return phrases
text = "The camera quality of this phone is amazing."
pipe(text, candidate_labels=extract_aspect(text))
[out]:
{'sequence': 'The camera quality of this phone is amazing.',
'labels': ['camera'],
'scores': [0.9983300566673279]}
Q: But the extracted keywords is not "right" or doesn't match the pre-defined ones?
A: No model is perfect and the model example above is a keyword extractor not a product aspect extractor. YMMV.
Q: Why isn't the zero-shot classifier giving me negative / positive labels?
A: The zero-shot classifier is labeling the data based on the extracted labels. Not a sentiment classifier.
<details>
<summary>英文:</summary>
Specific to the `yangheng/deberta-v3-base-absa-v1.1` model this is the usage and you have to loop through the model one time per aspect:
Load the ABSA model and tokenizer
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
for aspect in ['camera', 'phone']:
print(aspect, classifier('The camera quality of this phone is amazing.', text_pair=aspect))
[out]:
camera [{'label': 'Positive', 'score': 0.9967294931411743}]
phone [{'label': 'Neutral', 'score': 0.9472787380218506}]
----
To get the zero-shot classification scores in general, try using `pipeline`:
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from transformers import pipeline
Load the ABSA model and tokenizer
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
pipe = pipeline("zero-shot-classification", model=model, tokenizer=tokenizer)
pipe("The camera quality of this phone is amazing.", candidate_labels=["camera", "phone"])
[out]:
{'sequence': 'The camera quality of this phone is amazing.',
'labels': ['camera', 'phone'],
'scores': [0.9036691784858704, 0.09633082151412964]}
----
Depending on what "text generated aspect" means, perhaps it's keyword extraction, and if so, doing a search on https://huggingface.co/models?search=keyword, gives this as the top downloaded model, https://huggingface.co/yanekyuk/bert-uncased-keyword-extractor
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer2 = AutoTokenizer.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
model2 = AutoModelForTokenClassification.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
def extract_aspect(text):
extractor = pipeline("ner", model=model2, tokenizer=tokenizer2)
phrasesids = []
for tag in extractor(text):
if tag['entity'].startswith('B'):
phrasesids.append([tag['start'], tag['end']])
if tag['entity'].startswith('I'):
phrasesids[-1][-1] = tag['end']
phrases = [text
:p1] for p in phrasesids]
return phrases
text = "The camera quality of this phone is amazing."
extract_aspect(text)
[out]:
camera
Putting the extractor and classifier together:
from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
from transformers import pipeline
Load the ABSA model and tokenizer
model_name = "yangheng/deberta-v3-base-absa-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
classifier = pipeline("zero-shot-classification", model=model, tokenizer=tokenizer)
tokenizer2 = AutoTokenizer.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
model2 = AutoModelForTokenClassification.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
def extract_aspect(text):
extractor = pipeline("ner", model=model2, tokenizer=tokenizer2)
phrasesids = []
for tag in extractor(text):
if tag['entity'].startswith('B'):
phrasesids.append([tag['start'], tag['end']])
if tag['entity'].startswith('I'):
phrasesids[-1][-1] = tag['end']
phrases = [text
:p1] for p in phrasesids]
return phrases
text = "The camera quality of this phone is amazing."
pipe(text, candidate_labels=extract_aspect(text))
[out]:
{'sequence': 'The camera quality of this phone is amazing.',
'labels': ['camera'],
'scores': [0.9983300566673279]}
-----
### Q: But the extracted keywords is not "right" or doesn't match the pre-defined ones?
A: No model is perfect and the model example above is a keyword extractor not a product aspect extractor. YMMV.
### Q: Why isn't the zero-shot classifier giving me negative / positive labels?
A: The zero-shot classifier is labelling the data based on the extracted labels. Not a sentiment classifier.
</details>
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库,让每个人都能够通过互相帮助和分享经验来进步。
评论