Topic Memory Networks for Short Text Classification
Refereed conference paper presented and published in conference proceedings


全文

其它資訊
摘要Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on short text classification, meanwhile generates coherent topics.
出版社接受日期02.08.2018
著者Jichuan Zeng, Jing Li, Yan Song, Cuiyun Gao, Michael R. Lyu, Irwin King
會議名稱2018 Conference on Empirical Methods in Natural Language Processing
會議開始日31.10.2018
會議完結日04.11.2018
會議地點Brussels, Belgium
會議國家/地區比利時
出版年份2018
語言美式英語

上次更新時間 2019-17-10 於 12:45