如何使用摘要

摘要会压缩用户认为内容太长而无法阅读的内容。 该服务为三种类型的流派提供摘要解决方案：纯文本、对话和本机文档。 选择与要汇总的内容类型匹配的选项卡。

文本摘要缩短了用户认为读取时间过长的内容。 抽取式和抽象式摘要都是将文章、论文或文档简缩成关键句子。

抽取式摘要：通过提取共同表示原始内容中最重要或相关信息的句子来生成摘要。

抽象式摘要：通过从文档中生成概括主旨的句子来生成摘要。

以查询为中心的摘要：允许在汇总时使用查询。

这些功能中的每一项都可以在指定特定关注项时，围绕这些项进行总结。

该服务提供 API 使用的 AI 模型。 只需发送内容进行分析即可。

为便于导航，下面是指向每个服务相应部分的链接：

方面 Section
抽取式 抽取式摘要
抽象式 抽象式摘要
面向查询的 以查询为中心的摘要

Features

Tip

若要开始使用这些功能，请参阅 快速入门文章。

提取式摘要 API 使用自然语言处理技术在非结构化文本文档中查找关键句子。 这些句子共同传达了文档的主要想法。

提取摘要将返回排名分数作为系统响应的一部分，以及提取的句子及其在原始文档中的位置。 排名分数指示句子与文档的主理念有多相关。 该模型为每个句子提供 0 到 1（含 0 和 1）之间的分数，并按请求返回分数最高的句子。 例如，如果请求一个包含三个句子的摘要，则该服务将返回分数最高的三个句子。

Azure语言、关键短语提取中的另一个功能可以提取关键信息。 在关键短语提取和提取摘要之间做出决定时，请考虑以下因素：

  • 关键短语提取返回短语，而抽取式摘要返回句子。
  • 抽取式摘要返回带有排名分数的句子，并根据请求返回排名靠前的句子。
  • 抽取式摘要还返回以下位置信息：
    • 偏移量：每个所提取句子的起始位置。
    • 长度：每个提取的句子的长度。

确定如何处理数据（可选）

提交数据

将文档作为文本字符串提交到 API。 API 在收到请求时执行分析。 因为 API 是异步的，所以在发送 API 请求和接收结果之间可能存在延迟。

使用此功能时，API 结果在引入请求后 24 小时内可用，响应指示此可用性。 在此时间段后，结果将被清除，并且不再可用于检索。

获取文本摘要结果

从语言检测获得结果时，可以将结果流式传输到应用程序或将输出保存到本地系统上的文件中。

以下示例展示了你可能提交用于摘要处理的内容。 该内容摘自 Microsoft 博客文章 A holistic representation toward integrative AI。 本文只是一个示例。 API 可以接受更长的输入文本。 有关详细信息， 请参阅数据和服务限制。

“在 Microsoft，我们致力于推动人工智能技术超越现有水平，采用更全面、以人为本的方法来学习和理解。” 作为 Foundry Tools 的首席技术官，我一直在与一个惊人的科学家和工程师团队合作，将这一追求变成现实。 “在我的角色中，我以独特的视角看待人类认知的三个属性之间的关系：语言文本 (X)、音频或视觉传感器信号(Y) 和多语言 (Z)。” 在所有这三个属性的交点，都有一些神奇之处，如图 1 所示，我们称之为 XYZ 代码，它是一种联合表示，可以创造出更强大的 AI，它能说、听、看和更好地理解人类。 我们相信 XYZ 代码将使我们能够实现长期愿景：跨领域迁移学习、跨越模式和语言。 目标是拥有可以联合学习表示以支持广泛的下游 AI 任务的预训练模型，就像人们现在所做的。 在过去的五年里，我们在对话语音识别、机器翻译、对话式问答、机器阅读理解和图像标题方面实现了人类在基准测试方面的表现。 这五项突破向我们发出了强烈的信号，表明我们更雄心勃勃的愿望，即实现 AI 功能的飞跃，实现多感官和多语言学习，这更符合人类学习和理解的方式。 我相信，只要以外部知识源为基础，联合 XYZ 代码是这一愿景的基础组成部分，特别是在下游 AI 任务中。

收到请求后，通过为 API 后端创建作业来处理文本摘要 API 请求。 如果作业成功，将返回 API 的输出。 输出结果将在24小时内可供检索。 此时间过后，输出将被清除。 由于多语言和表情符号的支持，响应中可能会出现文本位置偏移。 有关详细信息，请参阅如何处理偏移量。

使用前面的示例时，API 可能会返回以下汇总句子：

抽取式摘要：

  • “在Microsoft，我们正寻求通过采取更全面、以人为中心的方法来学习和理解来推进 AI 超越现有技术。
  • “我们相信 XYZ 代码将使我们能够实现长期愿景：跨领域迁移学习、跨越模式和语言。”
  • 目标是拥有可以联合学习表示以支持广泛的下游 AI 任务的预训练模型，就像人们现在所做的。

抽象式摘要：

  • “Microsoft正在采取更全面、以人为中心的学习和理解方法。 我们相信 XYZ 代码将使我们能够实现长期愿景：跨领域迁移学习、跨越模式和语言。 在过去的五年里，我们在关键基准测试上达到了人类水平的表现。

试用文本抽取式摘要

可以使用文本抽取式摘要来获取文章、论文或文档的摘要。 若要查看示例，请参阅快速入门文章。

使用 sentenceCount 参数来指导返回的句子数，默认值 3 为默认值。 范围为 1 到 20。

使用 sortby 参数可指定提取的句子按何种顺序返回，可以是 Offset 或 Rank，其中 Offset 为默认值。

参数值 Description
Rank 根据句子与输入文档的相关性（由服务决定）对句子进行排序。
Offset 保持句子在输入文档中出现的原始顺序。

试用文本抽象式摘要

以下示例演示如何开始使用文本抽象摘要：

  1. 将以下命令复制到文本编辑器中。 BASH 示例使用 \ 续行符。 如果你的控制台或终端使用不同的续行符，请改用相应符号。
curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-text/jobs?api-version=2023-04-01 \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: <your-language-resource-key>" \
-d \
' 
{
  "displayName": "Text Abstractive Summarization Task Example",
  "analysisInput": {
    "documents": [
      {
        "id": "1",
        "language": "en",
        "text": "At Microsoft, we have been on a quest to advance AI beyond existing techniques, by taking a more holistic, human-centric approach to learning and understanding. As Chief Technology Officer of Foundry Tools, I have been working with a team of amazing scientists and engineers to turn this quest into a reality. In my role, I enjoy a unique perspective in viewing the relationship among three attributes of human cognition: monolingual text (X), audio or visual sensory signals, (Y) and multilingual (Z). At the intersection of all three, there's magic—what we call XYZ-code as illustrated in Figure 1—a joint representation to create more powerful AI that can speak, hear, see, and understand humans better. We believe XYZ-code enables us to fulfill our long-term vision: cross-domain transfer learning, spanning modalities and languages. The goal is to have pretrained models that can jointly learn representations to support a broad range of downstream AI tasks, much in the way humans do today. Over the past five years, we have achieved human performance on benchmarks in conversational speech recognition, machine translation, conversational question answering, machine reading comprehension, and image captioning. These five breakthroughs provided us with strong signals toward our more ambitious aspiration to produce a leap in AI capabilities, achieving multi-sensory and multilingual learning that is closer in line with how humans learn and understand. I believe the joint XYZ-code is a foundational component of this aspiration, if grounded with external knowledge sources in the downstream AI tasks."
      }
    ]
  },
  "tasks": [
    {
      "kind": "AbstractiveSummarization",
      "taskName": "Text Abstractive Summarization Task 1",
    }
  ]
}
'

  1. 根据需要在命令中进行以下更改：

    • 将值 your-language-resource-key 替换为你的密钥。
    • 将请求 URL 的第一部分 (your-language-resource-endpoint) 替换为你的终结点 URL。

  2. 打开命令提示符窗口（例如 BASH）。

  3. 将文本编辑器中的命令粘贴到命令提示符窗口，然后运行命令。

  4. 从响应标头获取operation-location。 该值类似于以下 URL：

https://<your-language-resource-endpoint>/language/analyze-text/jobs/12345678-1234-1234-1234-12345678?api-version=2022-10-01-preview
  1. 若要获取请求的结果，请使用以下 cURL 命令。 请务必将 <my-job-id> 替换为从之前的 operation-location 响应头中收到的数值 ID 值：
curl -X GET https://<your-language-resource-endpoint>/language/analyze-text/jobs/<my-job-id>?api-version=2022-10-01-preview \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: <your-language-resource-key>"

抽象式文本摘要示例 JSON 响应

{
    "jobId": "cd6418fe-db86-4350-aec1-f0d7c91442a6",
    "lastUpdateDateTime": "2022-09-08T16:45:14Z",
    "createdDateTime": "2022-09-08T16:44:53Z",
    "expirationDateTime": "2022-09-09T16:44:53Z",
    "status": "succeeded",
    "errors": [],
    "displayName": "Text Abstractive Summarization Task Example",
    "tasks": {
        "completed": 1,
        "failed": 0,
        "inProgress": 0,
        "total": 1,
        "items": [
            {
                "kind": "AbstractiveSummarizationLROResults",
                "taskName": "Text Abstractive Summarization Task 1",
                "lastUpdateDateTime": "2022-09-08T16:45:14.0717206Z",
                "status": "succeeded",
                "results": {
                    "documents": [
                        {
                            "summaries": [
                                {
                                    "text": "Microsoft is taking a more holistic, human-centric approach to AI. We've developed a joint representation to create more powerful AI that can speak, hear, see, and understand humans better. We've achieved human performance on benchmarks in conversational speech recognition, machine translation, ...... and image captions.",
                                    "contexts": [
                                        {
                                            "offset": 0,
                                            "length": 247
                                        }
                                    ]
                                }
                            ],
                            "id": "1"
                        }
                    ],
                    "errors": [],
                    "modelVersion": "latest"
                }
            }
        ]
    }
}
参数 Description
-X POST <endpoint> 指定用于访问 API 的端点。
-H Content-Type: application/json 用于发送 JSON 数据的内容类型。
-H "Ocp-Apim-Subscription-Key:<key> 指定用于访问 API 的密钥。
-d <documents> 包含要发送的文档的 JSON。

以下 cURL 命令从 BASH shell 中执行。 请使用自己的资源名称、资源密钥和 JSON 值编辑这些命令。

基于查询的摘要

基于查询的文本摘要 API 是对现有文本摘要 API 的扩展。

最大的区别是请求正文中的新 query 字段（在 tasks>parameters>query 下面）。

Tip

基于查询的摘要在长度控制的使用方式上会因所采用的具体类型不同而有所差异：

  • 基于查询的提取摘要通过指定 sentenceCount支持长度控制。
  • 基于查询的抽象摘要不支持长度控制。

下面是一个示例请求：

curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-text/jobs?api-version=2023-11-15-preview \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: <your-language-resource-key>" \
-d \
' 
{
  "displayName": "Text Extractive Summarization Task Example",
  "analysisInput": {
    "documents": [
      {
        "id": "1",
        "language": "en",
        "text": "At Microsoft, we have been on a quest to advance AI beyond existing techniques, by taking a more holistic, human-centric approach to learning and understanding. As Chief Technology Officer of Foundry Tools, I have been working with a team of amazing scientists and engineers to turn this quest into a reality. In my role, I enjoy a unique perspective in viewing the relationship among three attributes of human cognition: monolingual text (X), audio or visual sensory signals, (Y) and multilingual (Z). At the intersection of all three, there's magic—what we call XYZ-code as illustrated in Figure 1—a joint representation to create more powerful AI that can speak, hear, see, and understand humans better. We believe XYZ-code enables us to fulfill our long-term vision: cross-domain transfer learning, spanning modalities and languages. The goal is to have pretrained models that can jointly learn representations to support a broad range of downstream AI tasks, much in the way humans do today. Over the past five years, we have achieved human performance on benchmarks in conversational speech recognition, machine translation, conversational question answering, machine reading comprehension, and image captioning. These five breakthroughs provided us with strong signals toward our more ambitious aspiration to produce a leap in AI capabilities, achieving multi-sensory and multilingual learning that is closer in line with how humans learn and understand. I believe the joint XYZ-code is a foundational component of this aspiration, if grounded with external knowledge sources in the downstream AI tasks."
      }
    ]
  },
"tasks": [
    {
      "kind": "AbstractiveSummarization",
      "taskName": "Query-based Abstractive Summarization",
      "parameters": {
          "query": "XYZ-code",
          "summaryLength": "short"
      }
    },    {
      "kind": "ExtractiveSummarization",
      "taskName": "Query_based Extractive Summarization",
      "parameters": {
          "query": "XYZ-code"
      }
    }
  ]
}
'

摘要长度控制

在抽象摘要中使用 summaryLength 参数

如果未指定 summaryLength，则模型将确定摘要长度。

对于 summaryLength 参数，接受三个值：

  • oneSentence：生成最多一个句子的摘要，其中包含大约 80 个标记。
  • short：生成最多两到三个句子的摘要，其中包含大约 120 个标记。
  • medium：生成最多 4 到 6 个句子的摘要，其中包含大约 170 个标记。
  • long：生成最多超过 7 个句子的摘要，其中包含大约 210 个标记。

下面是一个示例请求：

curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-text/jobs?api-version=2023-04-01 \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: <your-language-resource-key>" \
-d \
' 
{
  "displayName": "Text Abstractive Summarization Task Example",
  "analysisInput": {
    "documents": [
      {
        "id": "1",
        "language": "en",
        "text": "At Microsoft, we have been on a quest to advance AI beyond existing techniques, by taking a more holistic, human-centric approach to learning and understanding. As Chief Technology Officer of Foundry Tools, I have been working with a team of amazing scientists and engineers to turn this quest into a reality. In my role, I enjoy a unique perspective in viewing the relationship among three attributes of human cognition: monolingual text (X), audio or visual sensory signals, (Y) and multilingual (Z). At the intersection of all three, there's magic—what we call XYZ-code as illustrated in Figure 1—a joint representation to create more powerful AI that can speak, hear, see, and understand humans better. We believe XYZ-code enables us to fulfill our long-term vision: cross-domain transfer learning, spanning modalities and languages. The goal is to have pretrained models that can jointly learn representations to support a broad range of downstream AI tasks, much in the way humans do today. Over the past five years, we have achieved human performance on benchmarks in conversational speech recognition, machine translation, conversational question answering, machine reading comprehension, and image captioning. These five breakthroughs provided us with strong signals toward our more ambitious aspiration to produce a leap in AI capabilities, achieving multi-sensory and multilingual learning that is closer in line with how humans learn and understand. I believe the joint XYZ-code is a foundational component of this aspiration, if grounded with external knowledge sources in the downstream AI tasks."
      }
    ]
  },
  "tasks": [
    {
      "kind": "AbstractiveSummarization",
      "taskName": "Length controlled Abstractive Summarization",
          "parameters": {
          "summaryLength": "short"
      }
    }
  ]
}
'

在抽取式摘要中使用 sentenceCount 参数

sentenceCount对于参数，输入一个介于 1 到 20 的值，以指示所需的输出句子数。

下面是一个示例请求：

curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-text/jobs?api-version=2023-11-15-preview \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: <your-language-resource-key>" \
-d \
' 
{
  "displayName": "Text Extractive Summarization Task Example",
  "analysisInput": {
    "documents": [
      {
        "id": "1",
        "language": "en",
        "text": "At Microsoft, we have been on a quest to advance AI beyond existing techniques, by taking a more holistic, human-centric approach to learning and understanding. As Chief Technology Officer of Foundry Tools, I have been working with a team of amazing scientists and engineers to turn this quest into a reality. In my role, I enjoy a unique perspective in viewing the relationship among three attributes of human cognition: monolingual text (X), audio or visual sensory signals, (Y) and multilingual (Z). At the intersection of all three, there's magic—what we call XYZ-code as illustrated in Figure 1—a joint representation to create more powerful AI that can speak, hear, see, and understand humans better. We believe XYZ-code enables us to fulfill our long-term vision: cross-domain transfer learning, spanning modalities and languages. The goal is to have pretrained models that can jointly learn representations to support a broad range of downstream AI tasks, much in the way humans do today. Over the past five years, we have achieved human performance on benchmarks in conversational speech recognition, machine translation, conversational question answering, machine reading comprehension, and image captioning. These five breakthroughs provided us with strong signals toward our more ambitious aspiration to produce a leap in AI capabilities, achieving multi-sensory and multilingual learning that is closer in line with how humans learn and understand. I believe the joint XYZ-code is a foundational component of this aspiration, if grounded with external knowledge sources in the downstream AI tasks."
      }
    ]
  },
"tasks": [
    {
      "kind": "ExtractiveSummarization",
      "taskName": "Length controlled Extractive Summarization",
      "parameters": {
          "sentenceCount": "5"
      }
    }
  ]
}
'

服务和数据限制

有关每分钟和每秒可以发送的请求大小和数量信息，请参阅服务限制一文。

另见

  • Last updated on