Related papers: RoChBert: Towards Robust BERT Fine-tuning for Chin…

Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with…

Encoder-only Transformers have advanced along three axes -- architecture, data, and systems -- yielding Pareto gains in accuracy, speed, and memory efficiency. Yet these improvements have not fully transferred to Chinese, where tokenization…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Background: Identifying relationships between clinical events and temporal expressions is a key challenge in meaningfully analyzing clinical text for use in advanced AI applications. While previous studies exist, the state-of-the-art…

Deep learning has shown promising performance on various machine learning tasks. Nevertheless, the uninterpretability of deep learning models severely restricts the usage domains that require feature explanations, such as text correction.…

Pretrained language models (PLMs) have shown marvelous improvements across various NLP tasks. Most Chinese PLMs simply treat an input text as a sequence of characters, and completely ignore word information. Although Whole Word Masking can…

We present FireBERT, a set of three proof-of-concept NLP classifiers hardened against TextFooler-style word-perturbation by producing diverse alternatives to original samples. In one approach, we co-tune BERT against the training data and…

Chinese sequence labeling tasks are heavily reliant on accurate word boundary demarcation. Although current pre-trained language models (PLMs) have achieved substantial gains on these tasks, they rarely explicitly incorporate boundary…

There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously. It is unclear, however, how the models will perform in realistic scenarios…

Deep neural networks are susceptible to adversarial examples, posing a significant security risk in critical applications. Adversarial Training (AT) is a well-established technique to enhance adversarial robustness, but it often comes at…

We introduce SetBERT, a fine-tuned BERT-based model designed to enhance query embeddings for set operations and Boolean logic queries, such as Intersection (AND), Difference (NOT), and Union (OR). SetBERT significantly improves retrieval…

The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the final goal of lightening up political deliberation to…

Recent advancements in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks. While various defence mechanisms have been proposed, there is a lack of comprehensive benchmarks that…

Chinese word segmentation (CWS) is a fundamental task for Chinese language understanding. Recently, neural network-based models have attained superior performance in solving the in-domain CWS task. Last year, Bidirectional Encoder…

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…

Despite significant progress having been made in question answering on tabular data (Table QA), it's unclear whether, and to what extent existing Table QA models are robust to task-specific perturbations, e.g., replacing key question…

Adversarial training is one of the best-performing methods in improving the robustness of deep language models. However, robust models come at the cost of high time consumption, as they require multi-step gradient ascents or word…

Systemic Functional Grammar and its branch, Cardiff Grammar, have been widely applied to discourse analysis, semantic function research, and other tasks across various languages and texts. However, an automatic annotation system based on…

Chinese BERT models achieve remarkable progress in dealing with grammatical errors of word substitution. However, they fail to handle word insertion and deletion because BERT assumes the existence of a word at each position. To address…

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…