亞馬遜訓練alexa的方法

介紹 (Introduction)

Looking at the chatbot development tools and environments currently available, there are three ailments which require remedy:

查看當前可用的聊天機器人開發(fā)工具和環(huán)境，有三種需要補救的疾病：

• Compound Contextual Entities

  復合上下文實體

• Entity Decomposition

  實體分解

• Deprecation of Rigid State Machine, Dialog Management

  棄用剛性狀態(tài)機，對話框管理

The aim of Alexa Conversations is to take voice interactions from one shot interactions to multi-turn interactions. More complex conversations like booking a flight, ordering food or banking demands multi-turn conversations.

Alexa對話的目的是將語音互動從一次射擊互動轉(zhuǎn)變?yōu)槎嗷睾匣印?更復雜的對話(例如預訂航班，訂購食物或銀行業(yè)務)需要多回合對話。

One could say conversational commerce demands an environment to develop multi-turn conversations fast and efficient. Amazon must have recognized this and Alexa Conversations is their foray into addressing this need.

可以說對話商務需要一種環(huán)境來快速有效地進行多輪對話。 亞馬遜一定已經(jīng)意識到這一點，而Alexa Conversations是他們滿足這一需求的嘗試。

復合上下文實體 (Compound Contextual Entities)

Huge strides have been made in this area and many chatbot ecosystems accommodate these.

在這一領域已經(jīng)取得了長足的進步，許多聊天機器人生態(tài)系統(tǒng)都適應了這些。

上下文實體 (Contextual Entities)

The process of annotating user utterances is a way of identifying entities by their context within a sentence.

注釋用戶話語的過程是一種通過句子中的上下文標識實體的方法。

Contextual Entity Annotation In IBM Watson AssistantIBM Watson Assistant中的上下文實體注釋

Often entities have a finite set of values which are defined. Then there are entities which cannot be represented by a finite list; like cities in the world or names, or addresses. These entity types have too many variations to be listed individually.

通常，實體具有一組定義的有限值。 還有一些實體不能用有限列表來表示。 例如世界上的城市或名稱或地址。 這些實體類型有太多變化，無法單獨列出。

For these entities, you must use annotations; entities defined by their contextual use. The entities are defined and detected via their context within the user utterance.

對于這些實體，必須使用批注； 由其上下文使用定義的實體。 實體是通過用戶話語中的上下文來定義和檢測的。

復合實體 (Compound Entities)

The basic premise is that users will utter multiple entities in one sentence.

基本前提是用戶將在一句話中說出多個實體。

Users will most probably express multiple entities within one utterance; referred to as compound entities.

用戶很可能會在一句話中表達多個實體。 稱為復合實體。

In the example below, there are four entities defined:

在下面的示例中，定義了四個實體：

• travel_mode
  travel_mode
• from_city
  from_city
• to_cyt
  to_cyt
• date_time
  約會時間

Extract of NLU.md File In Rasa ProjectRasa項目中NLU.md文件的提取

These entities can be detected within the first pass and confirmation solicited from the user.

可以在第一遍內(nèi)檢測到這些實體，并向用戶征求確認。

實體分解 (Entity Decomposition)

Microsoft LUIS方法 (The Microsoft LUIS Approach)

Entity decomposition is important for both intent prediction and for data extraction with the entity. The best way to explain this is by way of an example.

實體分解對于意圖預測和與實體的數(shù)據(jù)提取都很重要。 最好的解釋方式是通過示例。

We start by defining a single entity, called

我們首先定義一個稱為

• Travel Detail.

  旅行細節(jié) 。

Within this entity, we defined three sub-entities. You can think of this as nested entities or sub-types. The three sub-types defined are:

在這個實體中，我們定義了三個子實體。 您可以將其視為嵌套實體或子類型。 定義的三個子類型是：

• Time Frame
  大體時間
• Mode
  模式
• City
  市

From here, we have a sub-sub-type for City:

在這里，我們有一個City的子子類型：

• From City
  從城市出發(fā)
• To City
  前往城市

Adding Sub-Entities: ML Entity Composed of Smaller Sub-Entities添加子實體：由較小的子實體組成的ML實體 Annotated Intent Examples帶注釋的意圖示例

The leader in entity decomposition is Microsoft LUIS, you can read more about it here. I would say LUIS have a complete solution in this regards.

實體分解的領導者是Microsoft LUIS，您可以在此處了解更多信息。 我想說LUIS在這方面有一個完整的解決方案。

亞馬遜Alexa對話 (Amazon Alexa Conversations)

Conversations have a similar option, though not as complete and comprehensive as LUIS. Within conversations you can define entities, which Amazon refers to Slots.

對話具有類似的選擇，盡管不如LUIS完整和全面。 在對話中，您可以定義實體(Amazon指插槽)。

Amazon Alexa Conversations: Slot Type With Properties (Amazon Alexa對話 ：帶屬性的插槽類型( PCS)PCS )

The aim during the conversations is to fill these slots (entities). Within conversations you can create a slot with multiple properties attached to it. These properties can be seen as sub-slots or sub-categories which together constitute the higher order entity.

對話期間的目的是填補這些空缺(實體)。 在對話中，您可以創(chuàng)建一個具有多個屬性的插槽。 這些屬性可以看作是子時隙或子類別，它們共同構(gòu)成了更高階的實體。

Alexa Conversations introduces a new slot type custom with properties (PCS).

Alexa Conversations引入了一個新的具有屬性(PCS)的自定義插槽類型。

Constituting a collection of slots which are hierarchical. This can be used to pass structured data between build-time components such as API Definitions and response templates.

構(gòu)成一組分層的插槽。 這可用于在構(gòu)建時組件(例如API定義)和響應模板之間傳遞結(jié)構(gòu)化數(shù)據(jù)。

淘汰剛性狀態(tài)機對話框管理 (Deprecation Of Rigid State Machine Dialog Management)

Deprecating the state machine for dialog management demands a more abstract approach; many are not comfortable of relinquishing control to an AI model.

棄用狀態(tài)機進行對話管理需要一種更抽象的方法； 許多人不愿意放棄對AI模型的控制。

The aim of Alexa Conversations (AC) is to furnish developers with the tools to build a more natural feeling Alexa skill with fewer lines of code. AC is an AI-driven approach to dialog management that enables the creating of skills that users can interact with in a natural unconstrained manner. This AI-driven

Alexa Conversations( AC )的目的是為開發(fā)人員提供工具，以更少的代碼行構(gòu)建更自然的Alexa技能。 AC是一種由AI驅(qū)動的對話框管理方法，可以創(chuàng)建用戶可以自然而不受限制地進行交互的技能。 這種AI驅(qū)動

Alexa Conversations In The Alexa Development ConsoleAlexa開發(fā)控制臺中的Alexa對話

approach is more abstract, but more conversation driven from a development process. Sample dialogs are important, together with annotation of data.

方法更抽象，但是更多的對話是由開發(fā)過程驅(qū)動的。 樣本對話框以及數(shù)據(jù)注釋非常重要。

You provide Alexa with a set of dialogs to demonstrate the functionalities required for the skill.

您為Alexa提供了一組對話框，以演示該技能所需的功能。

The build time systems behind Alexa Conversations will take the dialogs and create thousands of variations of these examples. This build process takes quite a while to complete.

Alexa對話背后的構(gòu)建時間系統(tǒng)將采用對話框并創(chuàng)建這些示例的數(shù)千種變體。 此構(gòu)建過程需要相當長的時間才能完成。

Fortunately any errors are surfaced at the start of the process, which is convenient.

幸運的是，在過程開始時會出現(xiàn)任何錯誤，這很方便。

AC builds a statistical model which interpret customer inputs & predict the best response from the model.

AC建立了一個統(tǒng)計模型，該模型可以解釋客戶輸入并預測模型的最佳響應。

From that information, AC will be able to make accurate assumptions .

根據(jù)這些信息， AC將能夠做出準確的假設。

AC uses AI to bridge the gap between voice application you can build manually and the vast range of possible conversations.

AC使用AI彌合了您可以手動構(gòu)建的語音應用程序與各種可能的對話之間的鴻溝。

框架組件 (Framework Components)

The five build-time components are:

五個構(gòu)建時組件是：

• Dialogs
  對話方塊
• Slots
  插槽
• Utterance Sets
  話語集
• Response Templates
  響應模板
• API Definitions
  API定義

對話方塊 (Dialogs)

Dialogs are really example conversations between the user and Alexa you define. You cans see the conversation is multi-turn and complexity is really up to you to define.

對話框?qū)嶋H上是用戶與您定義的Alexa之間的示例對話。 您可以看到對話是多回合的，而復雜度確實取決于您。

Dialogs: Example Conversations對話框 ：對話示例

For the prototype there are three entities or slots we want to capture, and four dialog examples with four utterances each were sufficient. Again, these conversations or dialogs will be used by AC to create an AI model to produce a natural and adaptive dialog model.

對于原型，我們要捕獲三個實體或插槽，并且四個帶有四個發(fā)音的對話示例就足夠了。 同樣， AC將使用這些對話或?qū)υ捒騺韯?chuàng)建AI模型，以生成自然的自適應對話框模型。

插槽 (Slots)

Slots are really the entities you would like to fill during the conversation. Should the user utter all three required slots in the first utterance, the conversation will only have one dialog turn.

廣告位確實是您希望在對話期間填寫的實體。 如果用戶在第一聲中說出了所有三個必需的位置，則對話將只有一個對話轉(zhuǎn)彎。

Two Types of Slots: Value Slots and Properties兩種類型的廣告位 ：價值廣告位和屬性廣告位

The conversation can be longer of course, should it take more conversation turns to solicit the relative information from the user to fill the slots. The interesting part is the two types of slots or entities. The custom defined slots with values, and the one with properties.

當然，如果要花費更多的會話輪流從用戶那里獲取相關信息以填補空缺，則會話可以更長。 有趣的部分是插槽或?qū)嶓w的兩種類型。 自定義的插槽包含值，一個具有屬性。

Alexa Conversations introduces custom slot types with properties (PCS) to define the data passed between components. They can be singular or compound. As stated previously, compound entities or slots can be decomposed.

Alexa Conversations引入了具有屬性(PCS)的自定義插槽類型，以定義在組件之間傳遞的數(shù)據(jù)。 它們可以是單數(shù)或化合物 。 如前所述，復合實體或插槽可以分解。

Compound entities which can be decomposed will grow in implementation and you will start seeing it used in more frameworks.

可以分解的復合實體將在實現(xiàn)中增長，您將開始看到它在更多框架中的使用。

話語集 (Utterance Sets)

Utterance Sets are groups of utterances that users may say to Alexa, which can include slots. They are used when annotating User Input turns in a Dialog.

話語集是用戶可以對Alexa說的話語組，其中可以包括插槽。 當在對話框中注釋用戶輸入時使用它們。

This is the one big drawback I see in AC, is the fact for each permutation of slots/entities, examples need to be defined.

這是我在AC中看到的一個最大缺點，那就是對于插槽/實體的每個排列，都需要定義示例。

For example:

例如：

1. abc
2. a
3. b
4. c
5. ab
6. bc
7. ac

For the three slots/entities, seven example sets need to be given. Imagine how this expands, should you have more slots/entities.

對于三個插槽/實體，需要給出七個示例集。 想象一下，如果您有更多的廣告位/實體，它會如何擴展。

Utterance Sets話語集

響應模板 (Response Templates)

Responses are how Alexa responds to users in the form of audio and visual elements. They are used when annotating Alexa Response turns in a Dialog.

響應是Alexa以音頻和視頻元素的形式對用戶做出響應的方式。 在注釋Alexa響應時在對話框中使用它們。

Responses Defined定義的回應

API定義 (API Definitions)

API Definitions define interfaces with your back-end service using arguments as inputs and return as output.

API定義使用參數(shù)作為輸入定義與后端服務的接口，并作為輸出返回。

結(jié)論 (Conclusion)

AC is a definite a move in the right direction…

AC無疑是朝著正確方向邁進的一步。

善良 (The Good)

• The advent of compound slots/entities which can be decomposed. Adding data structures to Entities.
  可以分解的復合縫隙/實體的出現(xiàn)。 向?qū)嶓w添加數(shù)據(jù)結(jié)構(gòu)。
• Deprecating the state machine and creating an AI model to manage the conversation.
  棄用狀態(tài)機并創(chuàng)建AI模型來管理對話。
• Making voice assistants more conversational.
  使語音助手更具對話性。
• Contextually annotated entities/slots.
  上下文注釋的實體/插槽。
• Error messages during the building of the model were descriptive and helpful.
  建立模型期間的錯誤消息是描述性的且有幫助的。

不太好 (The Not So Good)

• It might sound negligible; but building the model takes a while. I found that the errors in my model was surfaced at the beginning of the model building process, and training stopped. Should your model have no errors, the build is long.
  聽起來微不足道； 但是建立模型需要一段時間。 我發(fā)現(xiàn)模型建立過程的開始就浮出了模型中的錯誤，并且訓練停止了。 如果您的模型沒有錯誤，則構(gòu)建時間很長。
• Defining utterance sets are cumbersome. Creating utterance sets for all possible permutations if you have a large number of slots/entities is not ideal.
  定義話語集很麻煩。 如果您有大量的廣告位/實體，則為所有可能的排列創(chuàng)建話語集是不理想的。
• It is complex, especially compared to an environment like Rasa. The art is to improve the conversational experience by introducing complex AI models; while simultaneously simplifying the development environment.
  它很復雜，特別是與Rasa這樣的環(huán)境相比。 技巧是通過引入復雜的AI模型來改善對話體驗； 同時簡化了開發(fā)環(huán)境。

在這里 (Read More Here)

翻譯自: https://medium.com/@CobusGreyling/alexa-conversations-is-a-new-ai-driven-approach-to-conversational-interfaces-fe8d2a562602

亞馬遜訓練alexa的方法

總結(jié)

以上是生活随笔為你收集整理的亚马逊训练alexa的方法_Alexa对话是AI驱动的对话界面新方法的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。