这些设置存储在导出的应用中,并使用 REST API 或 LUIS 门户进行更新。These settings are stored in the exported app and updated with the REST APIs or LUIS portal.
更改应用版本设置会将应用训练状态重置为“未训练”。Changing your app version settings resets your app training status to untrained.
了解规范化概念以及如何使用版本 API 更新这些设置或使用 LUIS 门户中的“管理”部分的“设置”页面。Learn concepts of normalization and how to use version APIs to update these settings or use the LUIS portal's Manage section, Settings page.
UI 设置UI setting
API 设置API setting
信息Information
使用非确定性定型Use non-deterministic training
UseAllTrainingData
训练使用一小部分负采样。Training uses a small percentage of negative sampling.如果要使用所有数据而不是小型负采样,请设置为 true。If you want to use all data instead of the small negative sampling, set to true.
规范化音调符号Normalize diacritics
NormalizeDiacritics
规范化音调符号在言语中使用音调符号,将字符替换为常规字符。Normalizing diacritics replaces the characters with diacritics in utterances with regular characters.此设置仅适用于支持音调符号的语言。This setting is only available on languages that support diacritics.
规范化标点Normalize punctuation
NormalizePunctuation
规范化标点表示在你的模型获得定型之前,以及在终结点查询获得预测之前,将从言语中删除标点。Normalizing punctuation means that before your models get trained and before your endpoint queries get predicted, punctuation will be removed from the utterances.