我正在尝试在我自己的数据上实现Tensorflow Textsum 模型。训练集包含大约 50k 篇文章。我没有更改 textsum 模型中的任何默认设置。目前，我的“平均损失”约为 1.5 到 3.0。但是，解码结果是“the”、“of”、“in”、“to”等列表。
解码
of in in and and to to to to to
of a in and and to to to to
cats s s and and and to to
参考
rift between officers and residents as killings persist in south bronx
among deaths in 2016, a heavy toll in pop music
kim jong un says north korea is preparing to test long range missile
在这个阶段我不期望太精确的结果，但我认为即使是随机单词列表也比'of in and and to to'更好。