首页|Researchers Submit Patent Application, 'Implicitly Annotating Textual Data in Conversational Messaging', for Approval (USPTO 20230409817)
Researchers Submit Patent Application, 'Implicitly Annotating Textual Data in Conversational Messaging', for Approval (USPTO 20230409817)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
News editors obtained the following quote from the background information supplied by the inventors:“Supervised classification task models are trained using examples consisting of utterances (strings of textin a natural language such as English), and a label which classifies the utterance into one of severalclasses (commonly called intents in the literature). For example, the classification may be as simpleas “Positive”, “Negative”, and “Neutral”, and one wishes to classify individual utterances based on thesentiment therein. “Yay that’s great” may be classified as “Positive” while “Terrible, just terrible” maybe classified as “Negative”. This is one simple example, and in general the classification ontology may bearbitrarily complex, with tens, hundreds, or more possible classes.
NETL
NSTL
