Watson NLU Order Of entities 返回
Watson NLU Order Of entities returned
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,但如果提到了不止一种教育,它不会按顺序 return 结果。
例如,如果一份简历包含高中和大学,则 return数据的顺序错误,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
}
如何订购从模型本身找到的结果?
在 NLU API 中有一个新的 mentions 参数 returns 当设置为 [=13= 时文本中实体的位置]真。然后您可以使用每个实体的起始索引来对它们进行排序。 See the NLU API reference。
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,但如果提到了不止一种教育,它不会按顺序 return 结果。
例如,如果一份简历包含高中和大学,则 return数据的顺序错误,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
}
如何订购从模型本身找到的结果?
在 NLU API 中有一个新的 mentions 参数 returns 当设置为 [=13= 时文本中实体的位置]真。然后您可以使用每个实体的起始索引来对它们进行排序。 See the NLU API reference。