Related papers: Adversarial Alignment of Multilingual Models for E…
Pretrained multilingual models exhibit the same social bias as models processing English texts. This systematic review analyzes emerging research that extends bias evaluation and mitigation approaches into multilingual and non-English…
Neural Machine Translation (NMT) models are known to suffer from noisy inputs. To make models robust, we generate adversarial augmentation samples that attack the model and preserve the source-side semantic meaning at the same time. To…
This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to…
Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…
Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…
We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding. The key idea is to introspect current mistakes and prioritize adversarial training steps to…
Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for…
Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…
Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages we consider. Besides,…
Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…
Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some characters or words in the original examples, only substitution…
We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of…
The research field of adversarial machine learning witnessed a significant interest in the last few years. A machine learner or model is secure if it can deliver main objectives with acceptable accuracy, efficiency, etc. while at the same…
Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing…
State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding…
Probabilistic topic modeling is a popular choice as the first step of crosslingual tasks to enable knowledge transfer and extract multilingual features. While many multilingual topic models have been developed, their assumptions on the…
Representation learning for speech emotion recognition is challenging due to labeled data sparsity issue and lack of gold standard references. In addition, there is much variability from input speech signals, human subjective perception of…
Fueled by recent advances of self-supervised models, pre-trained speech representations proved effective for the downstream speech emotion recognition (SER) task. Most prior works mainly focus on exploiting pre-trained representations and…