零样本分类与 QNLI

Python 中的自然语言处理（NLP）

Fouad Trad

Machine Learning Engineer

零样本分类

让模型为从未见过的标签分配文本
通过自然语言推断获得输出
适用场景：
- 内容打标签
- 客服支持
- 新闻筛选

一段文本"国家足球队昨日夺冠"，需在三个类别中分类：体育、科技、健康。

零样本分类流水线

from transformers import pipeline

zero_shot_classifier = pipeline(

  task="zero-shot-classification",

  model="MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli"
)

text = "The national football team won the cup yesterday."

candidate_labels = ["sports", "technology", "health"]

result = zero_shot_classifier(text, candidate_labels)

print(result)

{'sequence': 'The national football team won the cup yesterday.',
 'labels': ['sports', 'technology', 'health'], 
 'scores': [0.9948731064796448, 0.0029330444522202015, 0.002193822991102934]}

问题自然语言推断（QNLI）

判断段落中是否包含问题的答案
适用场景：
- 文档搜索
- 聊天机器人
- 信息检索

图示：QNLI 接收一段文本和一个问题，并返回一个分数。

QNLI 流水线

from transformers import pipeline

qnli_pipeline = pipeline(
    task="text-classification", 
    model="cross-encoder/qnli-electra-base"
    )

passage = "Penguins are found primarily in the Southern Hemisphere."

question = "Where do penguins live?"

result = qnli_pipeline({"text": question, "text_pair": passage})

print(result)

{'label': 'LABEL_0', 'score': 0.9951545000076294}

QNLI 流水线

from transformers import pipeline
qnli_pipeline = pipeline(
    task="text-classification", 
    model="cross-encoder/qnli-electra-base"
    )
passage = "Penguins are found primarily in the Southern Hemisphere."
question = "What is the capital of Paris?"
result = qnli_pipeline({"text": question, "text_pair": passage})
print(result)

{'label': 'LABEL_0', 'score': 0.008907231502234936}

Passons à la pratique !

Python 中的自然语言处理（NLP）