Question

我正在使用watson NLU和自定义模型从简历中提取教育实体。

到目前为止，它工作正常，但如果提到的教育不止一个，它就不会按顺序返回结果。

例如，如果简历包含高中和大学，则会以错误的顺序返回数据，如下所示：

 {
    "type": "GraduationYear",
    "text": "2007",
    "disambiguation": {
        "subtype": [
        "Date"
        ]
    },
    "count": 1
},
{
    "type": "Institution",
    "text": "Rahman Colledge",
    "disambiguation": {
        "subtype": [
        "CollegeUniversity"
        ]
    },
    "count": 1
},
{
    "type": "GraduationYear",
    "text": "2017",
    "disambiguation": {
        "subtype": [
        "Date"
        ]
    },
    "count": 1
},

{
    "type": "Institution",
    "text": "MIS Highschool",
    "disambiguation": {
        "subtype": [
        "School"
        ]
    },
    "count": 1
},
{
    "type": "EducationLevel",
    "text": "Diploma",
    "disambiguation": {
        "subtype": [
        "Degree"
        ]
    },
    "count": 1
},
{
    "type": "EducationLevel",
    "text": "High School Certfication",
    "disambiguation": {
        "subtype": [
        "Degree"
        ]
    },
    "count": 1
}

如何订购模型本身的结果？

Answer 1

NLU API中有一个新的提及参数，当设置为 true 时，该参数返回文本中实体的位置。然后，您可以使用每个实体的起始索引对它们进行排序。 See the NLU API reference。

Watson NLU实体订单返回

1 个答案: