Cohere/miracl-id-corpus-22-12

---
annotations_creators:
- expert-generated

language:
- id

multilinguality:
- multilingual

size_categories: []
source_datasets: []
tags: []

task_categories:
- text-retrieval

license:
- apache-2.0

task_ids:
- document-retrieval
---

# MIRACL (id) embedded with cohere.ai `multilingual-22-12` encoder

We encoded the [MIRACL dataset](https://huggingface.co/miracl) using the [cohere.ai](https://txt.cohere.ai/multilingual/) `multilingual-22-12` embedding model.

The query embeddings can be found in [Cohere/miracl-id-queries-22-12](https://huggingface.co/datasets/Cohere/miracl-id-queries-22-12) and the corpus embeddings can be found in [Cohere/miracl-id-corpus-22-12](https://huggingface.co/datasets/Cohere/miracl-id-corpus-22-12).

For the orginal datasets, see [miracl/miracl](https://huggingface.co/datasets/miracl/miracl) and [miracl/miracl-corpus](https://huggingface.co/datasets/miracl/miracl-corpus).

Dataset info:
> MIRACL 🌍🙌🌏 (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual retrieval dataset that focuses on search across 18 different languages, which collectively encompass over three billion native speakers around the world.
>
> The corpus for each language is prepared from a Wikipedia dump, where we keep only the plain text and discard images, tables, etc. Each article is segmented into multiple passages using WikiExtractor based on natural discourse units (e.g., `\n\n` in the wiki markup). Each of these passages comprises a "document" or unit of retrieval. We preserve the Wikipedia article title of each passage.

## Embeddings
We compute for `title+" "+text` the embeddings using our `multilingual-22-12` embedding model, a state-of-the-art model that works for semantic search in 100 languages. If you want to learn more about this model, have a look at [cohere.ai multilingual embedding model](https://txt.cohere.ai/multilingual/).

## Loading the dataset

In [miracl-id-corpus-22-12](https://huggingface.co/datasets/Cohere/miracl-id-corpus-22-12) we provide the corpus embeddings. Note, depending on the selected split, the respective files can be quite large.

You can either load the dataset like this:
```python
from datasets import load_dataset
docs = load_dataset(f"Cohere/miracl-id-corpus-22-12", split="train")
```

Or you can also stream it without downloading it before:
```python
from datasets import load_dataset
docs = load_dataset(f"Cohere/miracl-id-corpus-22-12", split="train", streaming=True)

for doc in docs:
docid = doc['docid']
title = doc['title']
text = doc['text']
emb = doc['emb']
```

## Search

Have a look at [miracl-id-queries-22-12](https://huggingface.co/datasets/Cohere/miracl-id-queries-22-12) where we provide the query embeddings for the MIRACL dataset.

To search in the documents, you must use **dot-product**.

And then compare this query embeddings either with a vector database (recommended) or directly computing the dot product.

A full search example:
```python
# Attention! For large datasets, this requires a lot of memory to store
# all document embeddings and to compute the dot product scores.
# Only use this for smaller datasets. For large datasets, use a vector DB

from datasets import load_dataset
import torch

#Load documents + embeddings
docs = load_dataset(f"Cohere/miracl-id-corpus-22-12", split="train")
doc_embeddings = torch.tensor(docs['emb'])

# Load queries
queries = load_dataset(f"Cohere/miracl-id-queries-22-12", split="dev")

# Select the first query as example
qid = 0
query = queries[qid]
query_embedding = torch.tensor(queries['emb'])

# Compute dot score between query embedding and document embeddings
dot_scores = torch.mm(query_embedding, doc_embeddings.transpose(0, 1))
top_k = torch.topk(dot_scores, k=3)

# Print results
print("Query:", query['query'])
for doc_id in top_k.indices[0].tolist():
print(docs[doc_id]['title'])
print(docs[doc_id]['text'])
```

You can get embeddings for new queries using our API:
```python
#Run: pip install cohere
import cohere
co = cohere.Client(f"{api_key}") # You should add your cohere API Key here :))
texts = ['my search query']
response = co.embed(texts=texts, model='multilingual-22-12')
query_embedding = response.embeddings[0] # Get the embedding for the first text
```

## Performance

In the following table we compare the cohere multilingual-22-12 model with Elasticsearch version 8.6.0 lexical search (title and passage indexed as independent fields). Note that Elasticsearch doesn't support all languages that are part of the MIRACL dataset.

We compute nDCG@10 (a ranking based loss), as well as hit@3: Is at least one relevant document in the top-3 results. We find that hit@3 is easier to interpret, as it presents the number of queries for which a relevant document is found among the top-3 results.

Note: MIRACL only annotated a small fraction of passages (10 per query) for relevancy. Especially for larger Wikipedias (like English), we often found many more relevant passages. This is know as annotation holes. Real nDCG@10 and hit@3 performance is likely higher than depicted.

| Model | cohere multilingual-22-12 nDCG@10 | cohere multilingual-22-12 hit@3 | ES 8.6.0 nDCG@10 | ES 8.6.0 acc@3 |
|---|---|---|---|---|
| miracl-ar | 64.2 | 75.2 | 46.8 | 56.2 |
| miracl-bn | 61.5 | 75.7 | 49.2 | 60.1 |
| miracl-de | 44.4 | 60.7 | 19.6 | 29.8 |
| miracl-en | 44.6 | 62.2 | 30.2 | 43.2 |
| miracl-es | 47.0 | 74.1 | 27.0 | 47.2 |
| miracl-fi | 63.7 | 76.2 | 51.4 | 61.6 |
| miracl-fr | 46.8 | 57.1 | 17.0 | 21.6 |
| miracl-hi | 50.7 | 62.9 | 41.0 | 48.9 |
| miracl-id | 44.8 | 63.8 | 39.2 | 54.7 |
| miracl-ru | 49.2 | 66.9 | 25.4 | 36.7 |
| **Avg** | 51.7 | 67.5 | 34.7 | 46.0 |

Further languages (not supported by Elasticsearch):
| Model | cohere multilingual-22-12 nDCG@10 | cohere multilingual-22-12 hit@3 |
|---|---|---|
| miracl-fa | 44.8 | 53.6 |
| miracl-ja | 49.0 | 61.0 |
| miracl-ko | 50.9 | 64.8 |
| miracl-sw | 61.4 | 74.5 |
| miracl-te | 67.8 | 72.3 |
| miracl-th | 60.2 | 71.9 |
| miracl-yo | 56.4 | 62.2 |
| miracl-zh | 43.8 | 56.5 |
| **Avg** | 54.3 | 64.6 |

原始信息汇总

数据集概述

名称: MIRACL (Multilingual Information Retrieval Across a Continuum of Languages)

语言: 多语言，专注于18种语言

任务类型: 文本检索

许可证: Apache-2.0

数据来源: 维基百科数据，仅保留纯文本内容

数据处理: 使用WikiExtractor将文章分割成基于自然语篇单位的多个段落，每个段落作为一个检索单元

数据集详情

嵌入模型: 使用cohere.ai的multilingual-22-12嵌入模型，支持100种语言的语义搜索

数据集结构:

• 查询嵌入: 位于Cohere/miracl-id-queries-22-12
• 语料库嵌入: 位于Cohere/miracl-id-corpus-22-12

加载方法:

• 使用from datasets import load_dataset加载数据集
• 支持流式加载，无需预先下载

搜索方法:

• 使用点积计算查询嵌入与文档嵌入的相似度
• 推荐使用向量数据库进行大规模数据集的搜索

性能比较

评估指标: nDCG@10 和 hit@3

比较模型: cohere multilingual-22-12 与 Elasticsearch 8.6.0

结果:

• cohere multilingual-22-12 在多数语言上表现优于 Elasticsearch
• 平均nDCG@10: cohere multilingual-22-12为51.7，Elasticsearch为34.7
• 平均hit@3: cohere multilingual-22-12为67.5，Elasticsearch为46.0

注意: 由于仅对一小部分段落进行了相关性标注，实际性能可能更高。