Search Results for author:
Found 7 papers, 2 papers with code
Rethinking Textual Adversarial Defense for Pre-trained Language Models
However, we find that most existing textual adversarial examples are unnatural, which can be easily distinguished by both human and machine.
Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model
We question the validity of current evaluation of robustness of PrLMs based on these non-natural adversarial samples and propose an anomaly detector to evaluate the robustness of PrLMs with more natural adversarial samples.
Span Fine-tuning for Pre-trained Language Models
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words.
Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice
In detail, we design an auxiliary anomaly detection classifier and adopt a multi-task learning procedure, by which PrLMs are able to distinguish adversarial input samples.
Later Span Adaptation for Language Understanding
Instead of too early fixing the linguistic unit input as nearly all previous work did, we propose a novel method that combines span-level information into the representations generated by PrLMs during fine-tuning phase for better flexibility.
Enhancing Pre-trained Language Model with Lexical Simplification
By substituting complex words with simple alternatives, lexical simplification (LS) is a recognized method to reduce such lexical diversity, and therefore to improve the understandability of sentences.
