标签： luis
英语模型可以正确识别样本语音，但是某些日本模型无法识别它们。 特别是当我们将实体添加到意图中时，日语模型对样本话语的评分非常差。
答案 0 :(得分：0)
尚不完全支持日语。 Named Entity Recognition is currently in Preview。
注意以下几点也很重要
Because LUIS does not provide syntactic analysis and will not understand the difference between Keigo and informal Japanese, you need to incorporate the different levels of formality as training examples for your applications. でございます is not the same as です. です is not the same as だ.
那：
LUIS breaks an utterance into tokens based on culture. Several cultures return the entity object with the entity value tokenized. The startIndex and endIndex returned by LUIS in the entity object do not map to the new, tokenized value but instead to the original query in order for you to extract the raw entity programmatically.
LUIS breaks an utterance into tokens based on culture.
Several cultures return the entity object with the entity value tokenized. The startIndex and endIndex returned by LUIS in the entity object do not map to the new, tokenized value but instead to the original query in order for you to extract the raw entity programmatically.
很不幸，LUIS目前对日语没有很好的支持。 LUIS团队希望在2019年8月之前对令牌化进行重大改进，这将大大提高日语识别度。
以下是您可以尝试改善应用程序的一些内容：