简体繁体 English

复杂语句意图分类

[英]Complex Statements Intent Classification

原文 2018-04-25 04:06:36 3 1 nlp/ dialogflow/ luis/ wit.ai

Consider following sentences: 1) I want to watch movies watched by Srikanth but not by tarun 2) I want to watch movies of Christoper Nolan but not having Christian Bayle 3) I want watch movies watched by Srikanth but not liked by Tarun 请考虑以下句子：1）我想看Srikanth观看的电影，但不看塔伦（tarun）2）我想看Christoper Nolan的电影，但没有克里斯蒂安·贝勒3）我想看Srikanth观看的电影，但不喜欢Tarun

The problem I am facing is - Even though I can successfully define entities such as "not watched", "watched" , "not liked" , "having" , "not having" etc; 我面临的问题是-即使我可以成功定义诸如“未观看”，“已观看”，“不喜欢”，“有”，“没有”等实体； etc; 等等; Hence I will know what kind of action user is referring to. 因此，我将知道用户指的是哪种动作。 I will also get to know names like Srikanth, Tarun, Nolan, Bayle etc; 我还将认识一些名字，例如Srikanth，Tarun，Nolan，Bayle等； But How do I establish Relationship between name and action. 但是，我该如何建立名称与行动之间的关系。 How do i know which action was related to which name. 我怎么知道哪个动作与哪个名字有关。 I am not able to achieve this in LUIS / DIALOGFLOW. 我无法在LUIS / DIALOGFLOW中实现这一目标。

What I feel is only way is to break statement into 2 distinct statements, How can we do that and is that a right approahc 我认为唯一的方法是将语句分解为2个不同的语句，我们该怎么做，这是正确的方法

1 个解决方案

We cannot directly assign multiple intents to the same utterance through LUIS. 我们不能通过LUIS直接将多个意图分配给同一话语。 You can use NLTK along with LUIS to fix this issue as discussed here . 您可以使用NLTK与LUIS一起所讨论的解决此问题在这里。

Another workaround is to create 2 apps with each intent and assign the same utterances and add the code which would differentiate the intent based on the keyword in the sentence. 另一个解决方法是为每个意图创建2个应用程序并分配相同的发音，并添加基于句子中关键字区分意图的代码。