该网络不依赖于解析树,并且很容易适用于任何语言。我们通过四组实验对DCNN进行了测试:小尺度二值多类情绪预测、六向问题分类和推特远程监控情绪预测。该网络在前三个任务中都取得了优异的性能,在最后一个任务中相对于最强基线的误差减少了25%以上。 Convolutional Neural Networks for Sentence Classification--- Text...
DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision. The network achieves excellent performance in the first three tasks and a greater than 25% error reduction in the last task with ...
DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision. The network achieves excellent performance in the first three tasks and a greater than 25% error reduction in the last task with ...