luis.ai vs api.ai vs wit.ai 之间的比较?

Comparison between luis.ai vs api.ai vs wit.ai?

有谁知道这三者之间的具体区别和特点,或者如果开发者使用起来更features/more灵活?

blogpost has a really good analysis and comparison of Luis, Wit.ai, Api.ai, Amazon Alexa and IBM Watson services. It also has a nice background on why you would want to build a conversational bot in the first place and some of the challenges that come with that. It's written by the people behind YumiBot(为您提供应用程序开发报价的机器人)。

总的要点是 Wit.aiLuis 是不错的选择,如果你正在试验并且只是想获得免费的东西。 Api.ai 有很好的服务和用户体验,但不是免费的。与 IBM Watson 相同,后者为企业工作定价更高。 Alexa 的 API 很棒,但只能与 Alexa 一起使用(但鉴于他们拥有庞大的用户群,这不是一件坏事)。

他们的建议也是不要过分依赖一个供应商:

We would recommend you store all data needed for your model in a structured way in your own code repository. So later you can retrain the model from scratch, or even change the language understanding provider if needed. You just don’t want to be in a situation when a company shuts down their service and you are completely unprepared. Do you remember Parse?

希望对您有所帮助!我认为做出选择的最佳方式是尝试这些服务。鉴于其中许多仍在大量开发中并添加 features/changing 定价模型,您应该尝试使用特定的用例来处理它们,看看哪一个可以让您最快到达需要的地方。

wit.ai vs Dialogflow vs luis.ai

╔══════════════════════════════════════════════════════════════════════════════════════════════════════════════════════════════╗
║                                      wit.ai vs api.ai(Dialogflow) vs luis.ai                                                 ║
╠══════╦════════════════════════════════════╦═════════════════════════════════════════════╦════════════════════════════════════╣
║ S.No ║               Wit.ai               ║          Api.ai(Dialogflow)                 ║               Luis.ai              ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 1    ║ Wit.ai API is completely free      ║ Api.ai Has a paid enterprise option         ║ LUIS is in beta and free to use    ║
║      ║ with no limitations on             ║ which allows for this to be run on a        ║ 10K transactions per month         ║
║      ║ request rates.                     ║ private cloud internally and more           ║ and up to 5 requests per second    ║
║      ║                                    ║ from their services team., After google     ║ for each account.                  ║
║      ║                                    ║ acquisition they are providing free         ║                                    ║
║      ║                                    ║ services by integrating google cloud        ║                                    ║
║      ║                                    ║ services.                                   ║                                    ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 2    ║ Provides a nice combination        ║ Speech to Text and Text to Speech           ║ LUIS uses machine learning         ║
║      ║ of both voice recognition and      ║ capabilities, along with machine            ║ based methods to analyze           ║
║      ║ machine learning for developers.   ║ learning.                                   ║ sentences. To perform machine      ║
║      ║                                    ║                                             ║ learning, LUIS breaks an           ║
║      ║                                    ║                                             ║ utterance into "tokens".           ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 3    ║ Has two main elements to it        ║ Support of Intents, Entities, actions       ║ Supports Intents, Entities         ║
║      ║ that you set up within your        ║ and one key focus area is its “Domains”.    ║ and actions.                       ║
║      ║ app – intents and entities.        ║                                             ║                                    ║
║      ║ Actions are separated to           ║                                             ║                                    ║
║      ║ use as a combined operations.      ║                                             ║                                    ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 4    ║ Has pre-build entities like        ║ Has pre-build entities like @sys.date,      ║ Has pre-build entities             ║
║      ║ temperature, number, URLs,         ║ @sys.color, @sys.unit-currency… etc.        ║ builtin.intent.alarm,              ║
║      ║ emails, duration… etc.             ║                                             ║ builtin.intent.calendar,           ║
║      ║                                    ║                                             ║ builtin.intent.email… etc.         ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 5    ║ Doesn’t have integration module    ║ Has integration module to connect           ║ Has integration to Microsoft       ║
║      ║ to directly communicating with     ║ directly to Facebook messenger and          ║ Azure and other services, can be   ║
║      ║ Facebook messenger or other        ║ other messenger api’s. Has support for      ║ deployable in any supported        ║
║      ║ messenger APIs. but has web        ║ deploying in to heroku server, enterprise   ║ servers.                           ║
║      ║ service api to hook services.      ║ paid environment.                           ║                                    ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 6    ║ Early in 2015, joined Facebook     ║ Created by a team who built personal        ║ LUIS was introduced together with  ║
║      ║ and opened up the entire platform  ║ assistant app for major mobile platforms    ║ Microsoft Bot Framework and Skype  ║
║      ║ to be free for both public and     ║ with speech and text enabled conversations. ║ Developer Platform which can be    ║
║      ║ private instances.                 ║ acquired by google (sept 2016).             ║ used to create Skype Bots.         ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 7    ║ Wit.ai API for developers of iOS,  ║ Api.ai has SDKs for Android, iOS,           ║ LUIS allow building applications   ║
║      ║ Android, Node.js, Raspberry Pi,    ║ the Apple Watch, Node.js, Cordova,          ║ by using the LUIS web interface.   ║
║      ║ Ruby, Python, C, Rust and          ║ Unity, C#, Xamarin, Windows Phone,          ║ No coding needed other than the    ║
║      ║ Windows Phone. It even             ║ Python and JavaScript. It also can be       ║ ability to interpret and use the   ║
║      ║ has a JavaScript plugin for        ║ integrated with Amazon’s Echo and           ║ returned JSON in application.      ║
║      ║ front end developers.              ║ Microsoft’s Cortana.                        ║ It is also possible to use the     ║
║      ║                                    ║                                             ║ LUIS REST API for                  ║
║      ║                                    ║                                             ║ automation of applications.        ║
╚══════╩════════════════════════════════════╩═════════════════════════════════════════════╩════════════════════════════════════╝

更新: API.AI 现在是 Dialogflow。 Learn more here.

这个问题的一个方面是这些工具在理解自然语言方面的效率如何。在我们(Snips,一家法国人工智能公司)刚刚发布的近期基准测试中,我们测试了 Alexa(亚马逊)、SiriKit(苹果)、Luis(微软)和 API.ai 的 built-in 自然语言引擎(Google).

我们测试了他们理解自然查询的能力,例如“给我找一家我可以去参加午餐会议的沙拉吧”、“为 6 人叫一辆出租车”,以及其他 326 个查询。

总的来说,所有的解决方案都是不完美的。

更准确地说,它们在响应中都有相似的噪声水平(精度在 60% 到 90% 之间),但它们可以支持的语言范围存在显着差异。从这个角度来看,Luis 表现最差:在我们测试的每个用例中,它只能理解不到 14% 的查询。 API.ai 表现更好,尽管不是很可靠:它可以理解我们测试的 0% 到 80% 的查询,具体取决于用例。 Alexa(42% 和 82% 的召回率)和 Siri(61% 的召回率)的召回率最高。

更多详细信息以及这些结果背后的原始数据可以在我们的博客 post、Benchmarking Natural Language Understanding Systems

中找到

我们最近 published an evaluation study of seven NLU API-enabled services:API.ai、Amazon Lex、Microsoft LUIS、IBM Watson Conversation、wit.ai、Recast.ai 和 Snips.ai。

我们调查结果的简要总结:

  • IBM Watson 意图检测是最好的,尤其是在较小的训练数据集上(尽管在超过 2000 个样本上训练时,差异是无法区分的)。
  • API.AI是免费的,在足够大的训练集上的性能与 IBM Watson 和 Microsoft LUIS 相当。
  • 在我们的测试中,Microsoft LUIS 的运行速度明显快于其他软件。 wit.ai 性能和响应时间比上面三个稍差,但它是免费的,并且提供最好的语言覆盖(大约 50 种语言)。
  • A​​mazon Lex 有相当严格的 API 限制(训练集大小限制为 200K 个符号,这可能不足以达到多意图助手的良好意图检测质量;还需要所有训练由实体标记的话语,这使得数据集的准备变得复杂。

我认为 Luis 更健壮,可以提取不同语言的实体。 我在 api.ai 中测试过,但荷兰语对我不起作用。 如果您只需要英语,那么其中任何一种都应该没问题,但如果您需要支持更多语言,那么在使用一项服务之前最好也测试这些语言。 Bing 语音转文本没问题,但我认为要获得更强大的解决方案,您将需要另一个 Microsoft 服务来清除语音和噪音。

我将回答您关于灵活性和作为开发人员的问题的最后一部分,IMO 最终归结为您在这些平台中寻找的东西。

如果您是使用 NodeJS 或 .Net 的开发人员,LUIS.ai 有一个广泛的库和定义良好的代码片段和示例,可以非常快速地启动一个像样的机器人。与 google 相比,意图和实体识别略低于标准水平,但如果您是 Microsoft Shop,则可以一键集成 O365、Teams、Skype、cortana 等。[=23 的缺点=] 他们的服务似乎非常不稳定,在撰写本文时,他们的 LUIS.ai 网站无法正常运行,拒绝连接,并且已经超过一个星期,cortana 集成无法正常工作。因此,该平台仍在进行中。

Api.ai,从纯 NLU 的角度来看优于 Luis.ai,后续意图非常容易设置,语音启动远远优于 Luis.ai(即使在语音之后启动)。我想说的缺点是,构建机器人的连接能力和 API 比构建基于 MSBot 的聊天机器人要复杂一些。

另一个越来越受欢迎的开源平台是 RASA NLU。 https://rasa.com/。相比之下,大型数据集的实体识别和排名仍然有点粗略,但它是开源的,如果你想动手,你可以分叉他们的 github 平台并改进它。

从纯粹的开发角度来看,在 MS 平台(使用 luis.ai 或 qnamaker.ai )中飞起来聊天机器人更容易,但要准备好迎接挑战,因为他们致力于稳定平台.

-卡尔提克

我使用的是 DialogFlow,但后来切换到了 LUIS。为什么?因为当您在 DialogFlow 中调用 DetectIntent 时,您会得到一个带有所选意图及其置信度的 JSON,但我需要获得一个意图列表以及每个意图的置信度。 wit.ai 和 api.ai 也是如此。

另一方面,LUIS 会为您提供一个意图列表作为响应。这样,我就可以在我这边应用进一步的处理。

这是您搜索 "book flight to Cairo" 时来自 LUIS 的示例(LUIS 示例的一部分):

 {
   "query": "Book me a flight to Cairo",
   "topScoringIntent": {
       "intent": "BookFlight",
       "score": 0.9887482
   },
   "intents": [
       {
           "intent": "BookFlight",
           "score": 0.9887482
       },
       {
           "intent": "None",
           "score": 0.04272597
       },
       {
           "intent": "LocationFinder",
           "score": 0.0125702191
       },
       {
           "intent": "Reminder",
           "score": 0.00375502417
       },
       {
           "intent": "FoodOrder",
           "score": 3.765154E-07
       },
   ],
   "entities": [
       {
           "entity": "cairo",
           "type": "Location",
           "startIndex": 20,
           "endIndex": 24,
           "score": 0.956781447
       }
   ]
}

另一方面,配置 DialogFlow 的 UI 比 LUIS 强大得多。