嘿siri_嘿siri我可以帮你吗

嘿siri

Nuances, expressions, context, jargon, imprecision or social-cultural depth.

细微差别，表情，上下文，行话，不精确或社会文化深度。

Human language is diverse, its own, and can lead to a wide spectrum of interpretations. Are machines capable of understanding what we mean?

^ h乌曼语言是多样的，自己的，并可能导致解释的很广。 机器能够理解我们的意思吗？

And even more… Are they able to communicate back in a way that we can understand? If this is true, we have achieved one of the first objectives of Artificial Intelligence.

甚至更多…… 他们是否能够以我们可以理解的方式进行交流？ 如果这是真的，那么我们已经实现了人工智能的首要目标之一 。

Human language is a challenging area for AI.

人类语言是人工智能的一个挑战领域。

What’s the pattern to follow?

遵循的模式是什么？

If you want to learn more, go visit oscargarciaramos.com

如果您想了解更多，请访问 oscargarciaramos.com

对话互动 (Conversational interaction)

One of the seven patterns of AI, among hyperpersonalization, autonomous systems, predictive analytics and decision support, patterns and anomalies, recognition systems, goal-driven systems and, what we are talking about today, conversational/human interactions.

AI的七种模式之一 ，包括超个性化，自治系统，预测分析和决策支持，模式和异常，识别系统，目标驱动系统，以及我们今天所说的对话/人际互动。

What’s the main goal?

主要目标是什么？

Allow machines to be able to interact with humans through human language patterns, and machines to be able to communicate back to humans in a way they can understand.

允许机器能够通过人类语言模式与人类进行交互，并使机器能够以他们能够理解的方式与人类进行交流。

No more clicking, typing, swiping, or programming … We are too lazy.

不再需要单击，打字，滑动或编程… 我们太懒了 。

Now we want machines to interact with us in the same way that we communicate with each other. This includes voice, writing, or whatever method our wired brain is capable of understanding.

现在，我们希望机器以彼此通信的相同方式与我们交互。 这包括语音，书写或我们的有线大脑能够理解的任何方法。

There are three scenarios: Machine to human, machine to machine, and human to machine interactions.

共有三种方案 ：机器对人，机器对机器以及人对机器的交互。

Some examples are found in voice assistants, intention analysis, content generation, mood analysis, sentiment analysis or chatbots; developing solutions in cross-cutting sectors such as the financial sector or telemedicine.

在语音助手，意图分析，内容生成，情绪分析，情感分析或聊天机器人中可以找到一些示例。 在金融或远程医疗等跨部门领域中开发解决方案。

Mood, intent, sentiment, visual gestures, … These shapes or concepts are already understandable to the machine.

情绪，意图，情感，视觉手势等……这些形状或概念已经为机器所理解。

自然语言处理 (Natural Language Processing)

There’s a difference between ASR (Automatic Speech Recognition), STT (Speech to Text) and NLP (Natural Language Processing). While the first two, ASR & STT, are based on the transformation or generation of sound waves that are converted into words, the third one, NLP, interprets the data it hears. Not for this reason, AI (and Deep Learning) is no longer important in ASR & STT fields, since it has helped make speech-to-text more precise and text-to-speech more human.

ASR(自动语音识别) ， STT(语音到文本)和NLP(自然语言处理)之间是有区别的。 前两个是ASR和STT，它们是基于声波的转换或生成，然后将它们转换为单词，而第三个是NLP，它解释它所听到的数据。 并非出于这个原因，人工智能(和深度学习)在ASR和STT领域中不再重要，因为它有助于使语音转文本更加精确，文本转语音更加人性化。

However, Natural Language Processing (NLP) goes further than converting waves into words. We need to understand and provide understanding.

但是， 自然语言处理(NLP)比将wave转换成单词更进一步。 我们需要理解并提供理解 。

It’s here where we enter a huge world that ranges from the generation of speechs or texts, extraction and understanding of entities, detection and identification of topics or themes, connection of sentences, concepts, intentions and meanings.

在这里，我们进入一个巨大的世界，从语音或文本的生成，实体的提取和理解，主题或主题的检测和识别，句子，概念，意图和含义的连接。

基本上，理解。 (Basically, UNDERSTAND.)

Natural Language Processing is divided in TWO PARTS: natural language understanding and natural language generation.

自然语言处理分为两个部分： 自然语言理解和自然语言生成 。

Let’s see.

让我们来看看。

自然语言理解(NLU) (Natural Language Understanding (NLU))

NLU focuses on the interpretation of human input data such as voice or text to use it according to its intention. The MAIN goal is to understand the intention. How does it work?

NLU专注于解释人类输入数据(例如语音或文本)，以便根据其意图使用它。 主要目标是了解意图。 它是如何工作的？

AI ​​uses different tools such as lexical analysis to understand the sentences and their grammatical rules to later divide them into structural components.

AI使用诸如词法分析之类的不同工具来理解句子及其语法规则，随后将它们分为结构成分。

We use tools such as tokenization, lemmatization (a.k.a. stemming) or parsing to carry out these functions.

我们使用诸如标记化 ， lemmatization (aka词干 分析 )或解析之类的工具来执行这些功能。

• TOKENIZATION

  代币化

  Breaking up a string of characters into semantically meaningful parts that can be analyzed.

  将字符串分解成可以分析的语义上有意义的部分。

  No white spaces or comments.

  没有空格或注释。

• LEMMATIZATION

  合法化

  LEMMATIZATION(a.k.a. stemming) Identify and return the root words of the sentence to explore various additional information.

  语法化 (又 名词干化 )识别并返回句子的词根，以探索各种其他信息。

• PARSING

  解析

  Determining the syntactic structure of a text. There are two different approaches:

  确定文本的句法结构。 有两种不同的方法：

  dependency parsing, words as nodes and displaying links to its dependents.; and constituency parsing, displaying trees with the syntactic structure of a sentence using context-free grammar.

  依赖解析 ，将单词作为节点并显示到其依赖的链接。 和选区解析 ，使用上下文无关文法显示具有句子句法结构的树。

自然语言生成(NLG) (Natural Language Generation (NLG))

We first understand, then we answer.

我们首先了解，然后回答。

NLG is capable of preparing and making effective communication with humans in such a way that it does not seem that the speaker is a machine.

NLG能够以似乎说话者不是机器的方式来准备与人类进行有效的交流。

Broadly meant, it’s a software process that transforms structured data into natural language so it produces written or spoken narrative from a dataset.

广义上讲，这是一个软件过程，它将结构化数据转换为自然语言，从而从数据集中产生书面或口头叙述。

To do this, as we said before, the machine first needs to interpret the content and understand its meaning and then respond and carry out effective communication. At a high level, we carry out the following steps:

为此，如前所述，机器首先需要解释内容并理解其含义，然后做出响应并进行有效的通信。 在较高级别，我们执行以下步骤：

• Step 1: Content Determination, decide which information should be included in the text

  步骤1：确定内容，决定应在文本中包含哪些信息

• Step 2: Text Structure, setting reasonable order of organizing the text

  步骤2：文字结构，设定 组织文本的合理顺序

• Step 3: Sentence Aggregation, combining pieces of information in the same sentence.

  步骤3：句子聚合，将同一句子中的信息片段合并。

• Step 4: Grammaticalization, adopting natural language.

  步骤4：语法化，采用 自然语言。

• Step 5: Reference Expression Generation, similar to step 4, but identifying the domain of the content.

  步骤5：参考表达式生成，类似于步骤4，但标识内容的域。

• Step 6: Language Implementation, building a well-formed complete sentence.

  步骤6：语言实施，构建格式正确的完整句子。

Basic Formula → NLP = NLU+ NLG

基本公式→NLP = NLU + NLG

下一个是什么？ (So, what’s next?)

No more static content that generates nothing more than frustration and a waste of time for its users → Humans want to interact with machines that are efficient and effective.

没有更多的静态内容会给用户带来沮丧和浪费时间→人们希望与高效的机器交互。

Gone is the first ELIZA chatbot developed in 1966 that showed us the opportunities that this field could offer. However, current assistants such as Alexa, Google Assistant, Apple Siri or Microsoft Cortana, must improve when it comes to understanding humans and responding effectively, intelligently and in a consistent way.

Gone是1966年开发的第一个ELIZA聊天机器人 ，向我们展示了该领域可以提供的机会。 但是，当前的助手(例如Alexa ， Google Assistant ， Apple Siri或Microsoft Cortana)在理解人类并以一致的方式进行有效，智能地响应时必须提高。

They have no choice.

他们别无选择。

Let’s leverage the conversational pattern of AI.

让我们利用AI的对话模式 。

Feel free to leave a comment or share this post. Follow me for future posts.

随时发表评论或分享这篇文章。 跟 我 来以后的帖子。

And if you want to learn more, you can find me at oscargarciaramos.com

如果您想了解更多信息，可以在 oscargarciaramos.com上 找到我。

翻译自: https://towardsdatascience.com/hey-siri-can-i-help-you-4065f38ae869

嘿siri