Generative Adversarial Networks (GANs) have achieved great success in image synthesis, but have proven to be difficult to generate natural language. Challenges arise from the uninformative learning signals passed from the discriminator. In other word
s, the poor learning signals limit the learning capacity for generating languages with rich structures and semantics. In this paper, we propose to adopt the counter-contrastive learning (CCL) method to support the generator's training in language GANs. In contrast to standard GANs that adopt a simple binary classifier to discriminate whether a sample is real or fake, we employ a counter-contrastive learning signal that advances the training of language synthesizers by (1) pulling the language representations of generated and real samples together and (2) pushing apart representations of real samples to compete with the discriminator and thus prevent the discriminator from being overtrained. We evaluate our method on both synthetic and real benchmarks and yield competitive performance compared to previous GANs for adversarial sequence generation.
We propose the first general-purpose gradient-based adversarial attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix
, hence enabling gradient-based optimization. We empirically demonstrate that our white-box attack attains state-of-the-art attack performance on a variety of natural language tasks, outperforming prior work in terms of adversarial success rate with matching imperceptibility as per automated and human evaluation. Furthermore, we show that a powerful black-box transfer attack, enabled by sampling from the adversarial distribution, matches or exceeds existing methods, while only requiring hard-label outputs.
Recent studies have shown that deep neural network-based models are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. Howeve
r, there is a lack of systematic study on comparing different defense approaches under the same attacking setting. In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. In addition, we propose an effective method to further improve the robustness of neural text classifiers against such attacks, and achieved the highest accuracy on both clean and adversarial examples on AGNEWS and IMDB datasets by a significant margin. We hope this study could provide useful clues for future research on text adversarial defense. Codes are available at https://github.com/RockyLzy/TextDefender.
We propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed-attention mechanism, and employ gen
erative adversarial network architecture for pre-training language model and fine-tuning to the downstream multi-class classification task. Experiments were conducted on the SciCite datasets to compare model performance. Our proposed maGAN model achieved the best Macro-F1 of 0.8532.
Symptoms of the progress of the civil case are events or facts that the lawsuit is exposed to in terms of form and before entering into the matter, and which lead to the suspension or temporary suspension of the proceeding in the case. There are cert
ain symptoms that occur in the civil case, which make it in a state of temporary stagnation that prevents it from moving towards its desired goal Also, some of these symptoms are due to involuntary causes that occur without the litigants having a hand in their occurrence, or the ability to push them. Such as death, loss of capacity, or loss of legal representative status.
Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers. Despite being successful, the word sequences produced in s
uch attacks are often ungrammatical and can be easily distinguished from natural text. We develop adversarial attacks that appear closer to natural English phrases and yet confuse classification systems when added to benign inputs. We leverage an adversarially regularized autoencoder (ARAE) to generate triggers and propose a gradient-based search that aims to maximize the downstream classifier's prediction loss. Our attacks effectively reduce model accuracy on classification tasks while being less identifiable than prior models as per automatic detection metrics and human-subject studies. Our aim is to demonstrate that adversarial attacks can be made harder to detect than previously thought and to enable the development of appropriate defenses.
Advertising on e-commerce and social media sites deliver ad impressions at web scale on a daily basis driving value to both shoppers and advertisers. This scale necessitates programmatic ways of detecting unsuitable content in ads to safeguard custom
er experience and trust. This paper focusses on techniques for training text classification models under resource constraints, built as part of automated solutions for advertising content moderation. We show how weak supervision, curriculum learning and multi-lingual training can be applied effectively to fine-tune BERT and its variants for text classification tasks in conjunction with different data augmentation strategies. Our extensive experiments on multiple languages show that these techniques detect adversarial ad categories with a substantial gain in precision at high recall threshold over the baseline.
Sentiment analysis has come a long way for high-resource languages due to the availability of large annotated corpora. However, it still suffers from lack of training data for low-resource languages. To tackle this problem, we propose Conditional Lan
guage Adversarial Network (CLAN), an end-to-end neural architecture for cross-lingual sentiment analysis without cross-lingual supervision. CLAN differs from prior work in that it allows the adversarial training to be conditioned on both learned features and the sentiment prediction, to increase discriminativity for learned representation in the cross-lingual setting. Experimental results demonstrate that CLAN outperforms previous methods on the multilingual multi-domain Amazon review dataset. Our source code is released at https://github.com/hemanthkandula/clan.
The use of crowdworkers in NLP research is growing rapidly, in tandem with the exponential increase in research production in machine learning and AI. Ethical discussion regarding the use of crowdworkers within the NLP research community is typically
confined in scope to issues related to labor conditions such as fair pay. We draw attention to the lack of ethical considerations related to the various tasks performed by workers, including labeling, evaluation, and production. We find that the Final Rule, the common ethical framework used by researchers, did not anticipate the use of online crowdsourcing platforms for data collection, resulting in gaps between the spirit and practice of human-subjects ethics in NLP research. We enumerate common scenarios where crowdworkers performing NLP tasks are at risk of harm. We thus recommend that researchers evaluate these risks by considering the three ethical principles set up by the Belmont Report. We also clarify some common misconceptions regarding the Institutional Review Board (IRB) application. We hope this paper will serve to reopen the discussion within our community regarding the ethical use of crowdworkers.
Representation learning is widely used in NLP for a vast range of tasks. However, representations derived from text corpora often reflect social biases. This phenomenon is pervasive and consistent across different neural models, causing serious conce
rn. Previous methods mostly rely on a pre-specified, user-provided direction or suffer from unstable training. In this paper, we propose an adversarial disentangled debiasing model to dynamically decouple social bias attributes from the intermediate representations trained on the main task. We aim to denoise bias information while training on the downstream task, rather than completely remove social bias and pursue static unbiased representations. Experiments show the effectiveness of our method, both on the effect of debiasing and the main task performance.
