把文章贴出来看看呢。morelikethis，应该是用的空间向量模型来找最相似的，你看看那些词和词频是否相似

分词器smartcn，ik，stardardAnalyzer都试了一遍
查找“By default, the queried document is excluded from the response (include set to false).”的相似文本，居然查出了
By default, the queried document is excluded from the response (include set to false).
和
Note: In order to use the mlt feature a mlt_field needs to be either be stored, store term_vector or source needs to be enabled.两条
其他中文的也一样，总是会查出一些完全不相似的文本