machine-learning - 是用于将单词组合成句子的机器学习 api

Question

有许多用于扫描图像的机器学习 api，但它们只返回一堆标签。

https://azure.microsoft.com/en-gb/services/cognitive-services/computer-vision/

{ "tags": [ "train", "platform", "station", "building", "indoor", "subway", "track", "walking", "waiting", "pulling", "board", "people", "man", "luggage", "standing", "holding", "large", "woman", "yellow", "suitcase" ],  "confidence": 0.833099365 } ] }

有没有将这些组合成句子的api？MS Cognitive Vision 是唯一能产生完整字幕的

"captions": [ { "text": "people waiting at a train station",

谷歌情感分析可以将一个句子分成语法部分，但有没有相反的 api？

https://cloud.google.com/natural-language/docs/basics

INPUT:
"train", "platform", "station", "building", "indoor", "subway", "track", "walking", "waiting", "pulling", "board", "people",
 "man", "luggage", "standing", "holding", "large", "woman", "yellow", "suitcase"

OUTPUT:
"people waiting at a train station"