如何在Microsoft的LUIS上使用多个意图

Question

我正在与LUIS合作，并希望不仅管理和处理最高得分意图，而且还要管理和处理所有其他人。在这种特定情况下，当某人查询同一短语中的两件事时。

例如：“我想买苹果”（“购买”意图）和“我想卖香蕉”（“卖”意图）与“我想买香蕉和卖苹果”（“买”和“卖”意图在同一个话语上）。

我们的想法是定义一个阈值，该阈值将接受任何高于此置信度数的意图得分“有效”。

在一些测试中，我发现如果我们对同一个话语的意图非常少，这可以起作用。

但是，如果我们增加相同话语上的意图数量，结果会非常快地降低。

我提供了一些例子来澄清我的意思：下面的输出示例是在LUIS上生成的4个意图（“买”，“卖”，“无”和“恶作剧”）和1个实体（“水果”）

我想买苹果==>

{
  "query": "i want to buy apples",
  "topScoringIntent": {
    "intent": "Buy",
    "score": 0.999846
  },
  "intents": [
    {
      "intent": "Buy",
      "score": 0.999846
    },
    {
      "intent": "None",
      "score": 0.2572831
    },
    {
      "intent": "sell",
      "score": 2.32163586e-7
    },
    {
      "intent": "prank",
      "score": 2.32163146e-7
    }
  ],
  "entities": [
    {
      "entity": "apples",
      "type": "Fruit",
      "startIndex": 14,
      "endIndex": 19,
      "resolution": {
        "values": [
          "apple"
        ]
      }
    }
  ]
}

我想卖香蕉==>

{
  "query": "i want to sell bananas",
  "topScoringIntent": {
    "intent": "sell",
    "score": 0.999886036
  },
  "intents": [
    {
      "intent": "sell",
      "score": 0.999886036
    },
    {
      "intent": "None",
      "score": 0.253938943
    },
    {
      "intent": "Buy",
      "score": 2.71893583e-7
    },
    {
      "intent": "prank",
      "score": 1.97906232e-7
    }
  ],
  "entities": [
    {
      "entity": "bananas",
      "type": "Fruit",
      "startIndex": 15,
      "endIndex": 21,
      "resolution": {
        "values": [
          "banana"
        ]
      }
    }
  ]
}

我想吃披萨==>

{
  "query": "i want to eat a pizza",
  "topScoringIntent": {
    "intent": "prank",
    "score": 0.997353
  },
  "intents": [
    {
      "intent": "prank",
      "score": 0.997353
    },
    {
      "intent": "None",
      "score": 0.378299
    },
    {
      "intent": "sell",
      "score": 2.72957237e-7
    },
    {
      "intent": "Buy",
      "score": 1.54754474e-7
    }
  ],
  "entities": []
}

现在有了两个意图......每个人的得分开始急剧减少

我想买苹果并卖香蕉==>

{
  "query": "i want to buy apples and sell bananas",
  "topScoringIntent": {
    "intent": "sell",
    "score": 0.4442593
  },
  "intents": [
    {
      "intent": "sell",
      "score": 0.4442593
    },
    {
      "intent": "Buy",
      "score": 0.263670564
    },
    {
      "intent": "None",
      "score": 0.161728472
    },
    {
      "intent": "prank",
      "score": 5.190861e-9
    }
  ],
  "entities": [
    {
      "entity": "apples",
      "type": "Fruit",
      "startIndex": 14,
      "endIndex": 19,
      "resolution": {
        "values": [
          "apple"
        ]
      }
    },
    {
      "entity": "bananas",
      "type": "Fruit",
      "startIndex": 30,
      "endIndex": 36,
      "resolution": {
        "values": [
          "banana"
        ]
      }
    }
  ]
}

如果我们包含第三个意图，LUIS似乎崩溃了：

我想买苹果，卖香蕉和吃披萨==>

{
  "query": "i want to buy apples, sell bananas and eat a pizza",
  "topScoringIntent": {
    "intent": "None",
    "score": 0.139652014
  },
  "intents": [
    {
      "intent": "None",
      "score": 0.139652014
    },
    {
      "intent": "Buy",
      "score": 0.008631414
    },
    {
      "intent": "sell",
      "score": 0.005520768
    },
    {
      "intent": "prank",
      "score": 0.0000210663875
    }
  ],
  "entities": [
    {
      "entity": "apples",
      "type": "Fruit",
      "startIndex": 14,
      "endIndex": 19,
      "resolution": {
        "values": [
          "apple"
        ]
      }
    },
    {
      "entity": "bananas",
      "type": "Fruit",
      "startIndex": 27,
      "endIndex": 33,
      "resolution": {
        "values": [
          "banana"
        ]
      }
    }
  ]
}

您是否知道/建议我应该使用哪种方法来训练LUIS以缓解此问题？在同一个话语中处理多个意图是我的理由的关键。

非常感谢您的帮助。

Answer 1

您可能需要使用NLP对输入进行一些预处理，以便对句子进行分块，然后一次训练/提交一个块。我怀疑LUIS是否足够复杂以处理复合句中的多个意图。

下面是在Python中使用Spacy进行预处理的示例代码 - 没有对更复杂的句子进行测试，但这应该适用于您的例句。您可以使用以下段来提供给LUIS。

多个意图不是一个容易解决的问题，可能还有其他方法来处理它们

import spacy
model = 'en'

nlp = spacy.load(model)
print("Loaded model '%s'" % model)

doc = nlp("i want to buy apples, sell bananas and eat a pizza ")

for word in doc:
    if word.dep_ in ('dobj'):
        subtree_span = doc[word.left_edge.i : word.right_edge.i + 1]
        print(subtree_span.root.head.text + ' ' + subtree_span.text)
        print(subtree_span.text, '|', subtree_span.root.head.text)
        print()