LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification

Abstract

Recent work has shown that current sentiment classification models are fragile and sensitive to simple perturbations. In this work, we propose a novel adversarial training approach, LexicalAT, to improve the robustness of current sentiment classification models. The proposed approach consists of a generator and a classifier. The generator learns to generate examples to attack the classifier while the classifier learns to defend these attacks. Considering the diversity of attacks, the generator uses a large-scale lexical knowledge base, WordNet, to generate attacking examples by replacing some words in training examples with their synonyms (e.g., sad and unhappy), neighbor words (e.g., fox and wolf), or supersuperior words (e.g., chair and armchair). Due to the discrete generation step in the generator, we use policy gradient, a reinforcement learning approach, to train the two modules. Experiments show LexicalAT outperforms strong baselines and reduces test errors on various neural networks, including CNN, RNN, and BERT. 1

Reinforced Counterfactual Data Augmentation for Dual Sentiment Classification

“…Synonymous sample generation aimed to randomly replace some words in the real samples with their synonyms, hypernyms, or hyponyms from WordNet to generate a large amount of synonymous samples (Zhang et al, 2015;Kobayashi, 2018;Xu et al, 2019). However, these methods tend to suffer from the spurious association problem.…”

“…However, these methods tend to suffer from the spurious association problem. It is worth noting that our model is similar to Xu et al (2019), but there are a number of major differences. Firstly, it focused on generating synonymous samples with the same sentiment label, while our work aims to generate antonymous samples with the reversed sentiment label; Secondly, our discriminator contains an original-side predictor and an antonymous-side predictor which are paired for dual sentiment classification, and alleviate the spurious association problem.…”

“…The word substitution-based methods have been shown to be effective and stable in synonymous sentence generation. Inspired by Xu et al (2019), we propose to generate antonymous sentences based on word substitution. Specifically, we define three word substitution rules for each word in the sentence: no replacement, replacing with an antonym, and replacing with a synonym.…”

“…In policy gradient-based methods, it is a common practice to subtract a baseline reward from the current reward. The goal of the baseline reward r b is to enforce the generator to select x that yields a reward In contrast to Xu et al (2019) that only sampled one synonymous sentence for each sentence and defined r b as the expectation of the reward of all sampling sentences, we sample M antonymous sentences for each sentence, and use the average value of these M antonymous sentences as the baseline reward…”

“…Researchers have attempted to address this issue from two main perspectives: data augmentation and adversarial perturbation. The former tries to augment the training data by generating synonymous sentences (Zhang et al, 2015;Kobayashi, 2018;Xu et al, 2019); the latter aims to improve the generalization ability by applying perturbations to the word embeddings (Miyato et al, 2017;Croce et al, 2020). Although these methods have achieved sound performance, they still suffer from the spurious association problem.…”