论文标题
SCAT：文本数据的第二次机会自动编码器
SCAT: Second Chance Autoencoder for Textual Data
论文作者
论文摘要
我们为文本自动编码器（Second Chance AutoCododer（SCAT））提出了一种K竞争性学习方法。 SCAT选择$ K $最大和最小的阳性激活作为获奖者神经元，该神经元在学习过程中获得了失败者神经元的激活值，因此专注于检索主题的代表性良好的特征。我们的实验表明，与LDA，K-Sparse，NVCTM和Kate相比，SCAT在分类，主题建模和文档可视化方面取得了出色的性能。
We present a k-competitive learning approach for textual autoencoders named Second Chance Autoencoder (SCAT). SCAT selects the $k$ largest and smallest positive activations as the winner neurons, which gain the activation values of the loser neurons during the learning process, and thus focus on retrieving well-representative features for topics. Our experiments show that SCAT achieves outstanding performance in classification, topic modeling, and document visualization compared to LDA, K-Sparse, NVCTM, and KATE.
