Skip to content

Beyond text generation? #9

@pfliu-nlp

Description

@pfliu-nlp
  • 引入NLU任务:对NLU任务而言,evaluation-as-a-service的意义是什么?
    * 比如可以标注化evaluation库的版本(e.g., seqeval)
  • 引入benchmark:比如GLUE,价值是什么?

我们要总结下有哪些东西需要标准化?

  • NLG: 数据预处理(tokenize, capitalness, truncation)
  • NLG: metric自带的超参数
  • metric版本
  • 数据边界处理
  • .... (继续补充)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions