就像懂得逻辑连接(布尔运算AND)的人脑可以类似地将逻辑连接的句子分类那样,TLU也懂得一点逻辑连接之类的东西。
Insofar as a human brain that knows about logical conjunction (Boolean AND) would similarly classify logically conjoined sentences, this TLU knows something like logical conjunction.
因而只需对动词停止配价描写和分类,再用相应的题元与动词婚配,就可以生成句子了。
So as long as valence verbs to describe and classification, reoccupy corresponding question yuan and verbs, can generate sentence match.
用这些特征构成句子向量表示,并用机器学习的方法对其进行训练得到器,从而把自动文摘转换为分类问题。
There are eight features used to form the feature vector for each sentence, and the summarizer is gained by machine learning algorithms, so automatic summarization is changed into classification task.
应用推荐