快速入门

Sentence Transformer

Sentence Transformer (又名 bi-encoder) 模型的特性

计算给定文本或图像的固定大小向量表示 (嵌入)。
嵌入计算通常高效，嵌入相似度计算非常快。
适用于广泛的任务，例如语义文本相似度、语义搜索、聚类、分类、释义挖掘等等。
通常用作两步检索过程的第一步，其中 Cross-Encoder (又名 reranker) 模型用于重新排序来自 bi-encoder 的前 k 个结果。

一旦您安装了 Sentence Transformers，您就可以轻松使用 Sentence Transformer 模型

from sentence_transformers import SentenceTransformer

# 1. Load a pretrained Sentence Transformer model
model = SentenceTransformer("all-MiniLM-L6-v2")

# The sentences to encode
sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium.",
]

# 2. Calculate embeddings by calling model.encode()
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 3. Calculate the embedding similarities
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6660, 0.1046],
#         [0.6660, 1.0000, 0.1411],
#         [0.1046, 0.1411, 1.0000]])

使用 SentenceTransformer("all-MiniLM-L6-v2") 我们选择要加载的 Sentence Transformer 模型。在此示例中，我们加载 all-MiniLM-L6-v2，这是一个在超过 10 亿个训练对的大型数据集上微调的 MiniLM 模型。使用 SentenceTransformer.similarity()，我们计算所有句子对之间的相似度。正如预期的那样，前两个句子之间的相似度 (0.6660) 高于第一个和第三个句子之间 (0.1046) 或第二个和第三个句子之间 (0.1411) 的相似度。

微调 Sentence Transformer 模型很容易，只需要几行代码。有关更多信息，请参阅训练概述部分。

提示

阅读 Sentence Transformer > 使用方法 > 加速推理，了解如何将模型的推理速度提高 2 倍-3 倍的技巧。

Cross Encoder

Cross Encoder (又名 reranker) 模型的特性

计算给定文本对的相似度得分。
通常提供比 Sentence Transformer (又名 bi-encoder) 模型更优越的性能。
通常比 Sentence Transformer 模型更慢，因为它需要为每对而不是每个文本进行计算。
由于前两个特性，Cross Encoders 通常用于重新排序来自 Sentence Transformer 模型的前 k 个结果。

Cross Encoder (又名 reranker) 模型的使用方法与 Sentence Transformers 类似

from sentence_transformers.cross_encoder import CrossEncoder

# 1. Load a pretrained CrossEncoder model
model = CrossEncoder("cross-encoder/stsb-distilroberta-base")

# We want to compute the similarity between the query sentence...
query = "A man is eating pasta."

# ... and all sentences in the corpus
corpus = [
    "A man is eating food.",
    "A man is eating a piece of bread.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
    "A woman is playing violin.",
    "Two men pushed carts through the woods.",
    "A man is riding a white horse on an enclosed ground.",
    "A monkey is playing drums.",
    "A cheetah is running behind its prey.",
]

# 2. We rank all sentences in the corpus for the query
ranks = model.rank(query, corpus)

# Print the scores
print("Query: ", query)
for rank in ranks:
    print(f"{rank['score']:.2f}\t{corpus[rank['corpus_id']]}")
"""
Query:  A man is eating pasta.
0.67    A man is eating food.
0.34    A man is eating a piece of bread.
0.08    A man is riding a horse.
0.07    A man is riding a white horse on an enclosed ground.
0.01    The girl is carrying a baby.
0.01    Two men pushed carts through the woods.
0.01    A monkey is playing drums.
0.01    A woman is playing violin.
0.01    A cheetah is running behind its prey.
"""

# 3. Alternatively, you can also manually compute the score between two sentences
import numpy as np

sentence_combinations = [[query, sentence] for sentence in corpus]
scores = model.predict(sentence_combinations)

# Sort the scores in decreasing order to get the corpus indices
ranked_indices = np.argsort(scores)[::-1]
print("Scores:", scores)
print("Indices:", ranked_indices)
"""
Scores: [0.6732372, 0.34102544, 0.00542465, 0.07569341, 0.00525378, 0.00536814, 0.06676237, 0.00534825, 0.00516717]
Indices: [0 1 3 6 2 5 7 4 8]
"""

使用 CrossEncoder("cross-encoder/stsb-distilroberta-base") 我们选择要加载的 CrossEncoder 模型。在此示例中，我们加载 cross-encoder/stsb-distilroberta-base，这是一个在 STS Benchmark 数据集上微调的 DistilRoBERTa 模型。

下一步

接下来考虑阅读以下部分之一