相关论文: Using Adversarial Attacks to Reveal the Statistica…

Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine. Compared with MRC on a single passage, multi-passage MRC is more challenging,…

One reason pretraining on self-supervised linguistic tasks is effective is that it teaches models features that are helpful for language understanding. However, we want pretrained models to learn not only to represent linguistic features,…

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is…

Adversarial attacks expose important blind spots of deep learning systems. While word- and sentence-level attack scenarios mostly deal with finding semantic paraphrases of the input that fool NLP models, character-level attacks typically…

Multi-choice machine reading comprehension (MRC) requires models to choose the correct answer from candidate options given a passage and a question. Our research focuses dialogue-based MRC, where the passages are multi-turn dialogues. It…

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial…

Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage. MRC systems must not only answer question when necessary but also distinguish when no…

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we…

Machine Reading Comprehension (MRC) with multiple-choice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Convolutional Spatial…

Health mentioning classification (HMC) classifies an input text as health mention or not. Figurative and non-health mention of disease words makes the classification task challenging. Learning the context of the input text is the key to…

Reward models (RMs) are central to the alignment of language models (LMs). An RM often serves as a proxy for human preferences to guide downstream LM behavior. However, our understanding of RM behavior is limited. Our work (i) formalizes a…

Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary research suggests that…

The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack…

Machine reading comprehension(MRC) has attracted significant amounts of research attention recently, due to an increase of challenging reading comprehension datasets. In this paper, we aim to improve a MRC model's ability to determine…

Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…

Background: Deception detection through analysing language is a promising avenue using both human judgments and automated machine learning judgments. For both forms of credibility assessment, automated adversarial attacks that rewrite…

With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances. However, the existing works only target on…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Speaker recognition is increasingly used in several everyday applications including smart speakers, customer care centers and other speech-driven analytics. It is crucial to accurately evaluate and mitigate biases present in machine…