🚀 T5-large Sentiment Analysis Model
This is a sentiment analysis model based on the Transformer architecture. It can handle various sentiment analysis tasks and provides flexible output formats. It is an improved version of yuyijiong/Randeng-T5-large-sentiment-analysis-Chinese, which solves the overfitting problem. It is fine-tuned on multiple Chinese and English sentiment analysis datasets from IDEA-CCNL/Randeng-T5-784M-MultiTask-Chinese.
📦 Installation
No specific installation steps are provided in the original document, so this section is skipped.
💻 Usage Examples
Basic Usage
import evaluate
module = evaluate.load("yuyijiong/quad_match_score")
predictions=["food | good | food#taste | pos"]
references=["food | good | food#taste | pos & service | bad | service#general | neg"]
result=module.compute(predictions=predictions, references=references)
print(result)
Advanced Usage
import torch
from transformers import T5Tokenizer, AutoModelForSeq2SeqLM
tokenizer = T5Tokenizer.from_pretrained("yuyijiong/T5-large-sentiment-analysis-Chinese")
model = AutoModelForSeq2SeqLM.from_pretrained("yuyijiong/T5-large-sentiment-analysis-Chinese", device_map="auto")
generation_config=GenerationConfig.from_pretrained("yuyijiong/T5-large-sentiment-analysis-Chinese")
text = '情感四元组(对象 | 观点 | 方面 | 极性)抽取任务(观点可以较长): [个头大、口感不错,就是个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好。]'
input_ids = tokenizer(text,return_tensors="pt", padding=True)['input_ids'].cuda(0)
with torch.no_grad():
output = model.generate(input_ids=input_ids,generation_config=generation_config)
output_str = tokenizer.batch_decode(output, skip_special_tokens=True)
print(output_str)
Usage Examples
Q:sentiment quadruples (target | opinion | aspect | polarity) extraction task (opinion can be long): [个头大、口感不错,就是个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好。]
A:个头 | 大 | 商品#大小 | 积极 & 口感 | 不错 | 商品#口感 | 积极 & null | 个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好 | 商品#新鲜程度 | 消极
Q:sentiment quadruples (target | opinion | aspect | polarity) extraction task (opinion can be long, complete null): [个头大、口感不错,就是个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好。]
A:个头 | 大 | 商品#大小 | 积极 & 口感 | 不错 | 商品#口感 | 积极 & null (个别) | 有烂掉口子刻意用泥土封着,这样做不好 | 商品#新鲜程度 | 消极
Q:sentiment quadruples (target | opinion | aspect | polarity) extraction task (opinion as short as possible): [个头大、口感不错,就是个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好。]
A:个头 | 大 | 商品#大小 | 积极 & 口感 | 不错 | 商品#口感 | 积极
Q:sentiment triples (target | opinion | polarity) extraction task (opinion can be long, complete null): [个头大、口感不错,就是个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好。]
A:个头 | 大 | 积极 & 口感 | 不错 | 积极 & null (花生) | 个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好 | 消极
Q:Judge the sentiment polarity of the following comment: [个头大、口感不错,就是个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好。]
A:Neutral
Q:sentiment pairs (aspect | polarity) extraction task (aspect options: price#cost-performance/price#discount/price#level/food#appearance/food#portion/food#taste/food#recommendation): [个头大、口感不错,就是个别坏了的或者有烂掉口子刻意用泥土封着,这样做不好。]
A:food#portion | Positive & food#taste | Neutral
Q:sentiment quadruples (target | opinion | aspect | polarity) extraction task : [The hot dogs are good , yes , but the reason to get over here is the fantastic pork croquette sandwich , perfect on its supermarket squishy bun .]
A:hot dogs | good | food#quality | pos & pork croquette sandwich | fantastic | food#quality | pos & bun | perfect | food#quality | pos
📚 Documentation
Supported Sentiment Analysis Tasks
["quadruples (target | opinion | aspect | polarity)",
"pairs (target | opinion)",
"triples (target | opinion | aspect)",
"triples (target | opinion | polarity)",
"triples (target | aspect | polarity)",
"pairs (aspect | polarity)",
"pairs (opinion | polarity)",
"single (polarity)"]
Additional Conditions for Chinese Input
- Answer Style Control: You can control the style of the extracted opinions. For example, you can specify whether the opinions should be short or long.
(Opinions as short as possible)(Opinions can be long)
- Aspect Selection: You can specify the aspects for sentiment analysis. For example,
(Aspect options: product/logistics/merchant/platform)
- Completing Null Targets: You can allow the model to automatically guess the null targets. For example,
(Complete null)
Output Format
The output format is as follows:
'target1 | opinion1 | aspect1 | polarity1 & target2 | opinion2 | aspect2 | polarity2 ......'
Evaluation Metric
You can use the yuyijiong/quad_match_score evaluation metric to evaluate the model's performance.
Latest Version
The latest version of the model is yuyijiong/T5-large-sentiment-analysis-Chinese-MultiTask.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers Supports Multiple Languages#Fine-grained Sentiment Analysis#Multi-task Learning#Chinese-English Mixed