论文标题
多域文本分类的最大批量FROBENIUS NORM
Maximum Batch Frobenius Norm for Multi-Domain Text Classification
论文作者
论文摘要
由于深度学习的出现，多域文本分类（MDTC）已取得了非凡的成就。最近，许多努力致力于应用对抗性学习来提取域不变特征以产生最新的结果。但是，这些方法仍然面临一个挑战：将原始功能转换为域，不变会扭曲原始功能的分布，从而降低了学识渊博的功能的可区分性。为了解决此问题，我们首先研究了批处理分类矩阵的结构，并理论上证明了学识渊博的特征的可区分性与批处输出矩阵的Frobenius Norm具有正相关。基于这一发现，我们提出了一种最大批处理Frobenius Norm（MBF）方法，以提高MDTC的特征可区分性。两个MDTC基准测试的实验表明，我们的MBF方法可以有效地提高最先进的表现。
Multi-domain text classification (MDTC) has obtained remarkable achievements due to the advent of deep learning. Recently, many endeavors are devoted to applying adversarial learning to extract domain-invariant features to yield state-of-the-art results. However, these methods still face one challenge: transforming original features to be domain-invariant distorts the distributions of the original features, degrading the discriminability of the learned features. To address this issue, we first investigate the structure of the batch classification output matrix and theoretically justify that the discriminability of the learned features has a positive correlation with the Frobenius norm of the batch output matrix. Based on this finding, we propose a maximum batch Frobenius norm (MBF) method to boost the feature discriminability for MDTC. Experiments on two MDTC benchmarks show that our MBF approach can effectively advance the performance of the state-of-the-art.
