Co-Regularized Adversarial Learning for Multi-Domain Text Classification

01/30/2022
by   Yuan Wu, et al.
0

Multi-domain text classification (MDTC) aims to leverage all available resources from multiple domains to learn a predictive model that can generalize well on these domains. Recently, many MDTC methods adopt adversarial learning, shared-private paradigm, and entropy minimization to yield state-of-the-art results. However, these approaches face three issues: (1) Minimizing domain divergence can not fully guarantee the success of domain alignment; (2) Aligning marginal feature distributions can not fully guarantee the discriminability of the learned features; (3) Standard entropy minimization may make the predictions on unlabeled data over-confident, deteriorating the discriminability of the learned features. In order to address the above issues, we propose a co-regularized adversarial learning (CRAL) mechanism for MDTC. This approach constructs two diverse shared latent spaces, performs domain alignment in each of them, and punishes the disagreements of these two alignments with respect to the predictions on unlabeled data. Moreover, virtual adversarial training (VAT) with entropy minimization is incorporated to impose consistency regularization to the CRAL method. Experiments show that our model outperforms state-of-the-art methods on two MDTC benchmarks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/31/2021

Mixup Regularized Adversarial Networks for Multi-Domain Text Classification

Using the shared-private paradigm and adversarial training has significa...
research
09/18/2019

Dual Adversarial Co-Learning for Multi-Domain Text Classification

In this paper we propose a novel dual adversarial co-learning approach f...
research
01/29/2022

Maximum Batch Frobenius Norm for Multi-Domain Text Classification

Multi-domain text classification (MDTC) has obtained remarkable achievem...
research
02/19/2021

Conditional Adversarial Networks for Multi-Domain Text Classification

In this paper, we propose conditional adversarial networks (CANs), a fra...
research
04/26/2022

A Robust Contrastive Alignment Method For Multi-Domain Text Classification

Multi-domain text classification can automatically classify texts in var...
research
02/15/2018

Multinomial Adversarial Networks for Multi-Domain Text Classification

Many text classification tasks are known to be highly domain-dependent. ...
research
09/30/2020

Adversarial Semi-Supervised Multi-Domain Tracking

Neural networks for multi-domain learning empowers an effective combinat...

Please sign up or login with your details

Forgot password? Click here to reset