作者: Uday Kamath , John Liu , James Whitaker , Uday Kamath , John Liu
DOI: 10.1007/978-3-030-14596-5_7
关键词:
摘要: In the previous chapter, CNNs provided a way for neural networks to learn hierarchy of weights, resembling that n-gram classification on text. This approach proved be very effective sentiment analysis, or more broadly text classification. One disadvantages CNNs, however, is their inability model contextual information over long sequences.