(EMNLP2019)Aspect-basedSentimentClassificationwithAspect-specificGraph ConvolutionalNetworks

問題：傳統的捕獲semantic與aspect之間信息的算法有所侷限 LIMIT1:rnn+attention容易將原本對一個aspect無影響的word納入考慮（the current attention mechanism may lead to a given aspect mistakenly attending to syntactically unrelatedcontextwords

>>阅读原文<<