Opensearch Neural Sparse Encoding Multilingual V1

🚀 多语言v1版OpenSearch神经稀疏编码模型

本项目是一个多语言的学习型稀疏检索模型，可将文档编码为高维稀疏向量，通过内积计算相似度得分，在多语言检索任务中表现出色。

🚀 快速开始

模型选择

选择模型时，应综合考虑搜索相关性、模型推理和检索效率（FLOPS）。我们在 MIRACL 基准测试中对模型性能进行了评估（由于无大小写区分的主干模型无法对其进行编码，因此排除了 th 语言）。 我们建议使用最大比率剪枝法。

✨ 主要特性

模型概述

• 论文：Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers
• 微调示例：opensearch-sparse-model-tuning-sample

这是一个学习型稀疏检索模型，它将文档编码为 105879 维的 稀疏向量。对于查询，它仅使用分词器和权重查找表来生成稀疏向量。非零维度索引表示词汇表中对应的标记，权重表示该标记的重要性。相似度得分是查询/文档稀疏向量的内积。

OpenSearch 神经稀疏特征支持使用 Lucene 倒排索引进行学习型稀疏检索。链接：https://opensearch.org/docs/latest/query-dsl/specialized/neural-sparse/。可以使用 OpenSearch 高级 API 进行索引和搜索。

详细搜索相关性

💻 使用示例

基础用法

import json
import itertools
import torch

from transformers import AutoModelForMaskedLM, AutoTokenizer


# get sparse vector from dense vectors with shape batch_size * seq_len * vocab_size
def get_sparse_vector(feature, output, prune_ratio=0.1):
    values, _ = torch.max(output*feature["attention_mask"].unsqueeze(-1), dim=1)
    values = torch.log(1 + torch.relu(values))
    values[:,special_token_ids] = 0
    max_values = values.max(dim=-1)[0].unsqueeze(1) * prune_ratio
    return values * (values > max_values)
    
# transform the sparse vector to a dict of (token, weight)
def transform_sparse_vector_to_dict(sparse_vector):
    sample_indices,token_indices=torch.nonzero(sparse_vector,as_tuple=True)
    non_zero_values = sparse_vector[(sample_indices,token_indices)].tolist()
    number_of_tokens_for_each_sample = torch.bincount(sample_indices).cpu().tolist()
    tokens = [transform_sparse_vector_to_dict.id_to_token[_id] for _id in token_indices.tolist()]

    output = []
    end_idxs = list(itertools.accumulate([0]+number_of_tokens_for_each_sample))
    for i in range(len(end_idxs)-1):
        token_strings = tokens[end_idxs[i]:end_idxs[i+1]]
        weights = non_zero_values[end_idxs[i]:end_idxs[i+1]]
        output.append(dict(zip(token_strings, weights)))
    return output
    
# download the idf file from model hub. idf is used to give weights for query tokens
def get_tokenizer_idf(tokenizer):
    from huggingface_hub import hf_hub_download
    local_cached_path = hf_hub_download(repo_id="opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1", filename="idf.json")
    with open(local_cached_path) as f:
        idf = json.load(f)
    idf_vector = [0]*tokenizer.vocab_size
    for token,weight in idf.items():
        _id = tokenizer._convert_token_to_id_with_added_voc(token)
        idf_vector[_id]=weight
    return torch.tensor(idf_vector)

# load the model
model = AutoModelForMaskedLM.from_pretrained("opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1")
tokenizer = AutoTokenizer.from_pretrained("opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1")
idf = get_tokenizer_idf(tokenizer)

# set the special tokens and id_to_token transform for post-process
special_token_ids = [tokenizer.vocab[token] for token in tokenizer.special_tokens_map.values()]
get_sparse_vector.special_token_ids = special_token_ids
id_to_token = ["" for i in range(tokenizer.vocab_size)]
for token, _id in tokenizer.vocab.items():
    id_to_token[_id] = token
transform_sparse_vector_to_dict.id_to_token = id_to_token



query = "What's the weather in ny now?"
document = "Currently New York is rainy."

# encode the query
feature_query = tokenizer([query], padding=True, truncation=True, return_tensors='pt', return_token_type_ids=False)
input_ids = feature_query["input_ids"]
batch_size = input_ids.shape[0]
query_vector = torch.zeros(batch_size, tokenizer.vocab_size)
query_vector[torch.arange(batch_size).unsqueeze(-1), input_ids] = 1
query_sparse_vector = query_vector*idf

# encode the document
feature_document = tokenizer([document], padding=True, truncation=True, return_tensors='pt', return_token_type_ids=False)
output = model(**feature_document)[0]
document_sparse_vector = get_sparse_vector(feature_document, output)


# get similarity score
sim_score = torch.matmul(query_sparse_vector[0],document_sparse_vector[0])
print(sim_score)   # tensor(7.6317, grad_fn=<DotBackward0>)


query_token_weight = transform_sparse_vector_to_dict(query_sparse_vector)[0]
document_query_token_weight = transform_sparse_vector_to_dict(document_sparse_vector)[0]
for token in sorted(query_token_weight, key=lambda x:query_token_weight[x], reverse=True):
    if token in document_query_token_weight:
        print("score in query: %.4f, score in document: %.4f, token: %s"%(query_token_weight[token],document_query_token_weight[token],token))
        

        
# result:
# score in query: 3.0699, score in document: 1.2821, token: weather
# score in query: 1.6406, score in document: 0.9018, token: now
# score in query: 1.6108, score in document: 0.3141, token: ?
# score in query: 1.2721, score in document: 1.3446, token: ny

上述代码示例展示了神经稀疏搜索的一个示例。尽管原始查询和文档中没有重叠的标记，但该模型仍能实现良好的匹配。

📄 许可证

本项目采用 Apache v2.0 许可证。

📚 详细文档

版权信息

版权归 OpenSearch 贡献者所有。详情请见 NOTICE。

支持语言