activity
20202023
most citedA Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning

22 citations · 48 across the 12 of their papers we have counts for

collaborators

14 papers

cs.CL20232 cited

Language models are not naysayers: An analysis of language models on negation benchmarks

Thinh Hung Truong, Timothy Baldwin, Karin Verspoor +1

Negation has been shown to be a major bottleneck for masked language models, such as BERT. However, whether this finding still holds for larger-sized auto-regressive language model…

cs.LG20223 cited

Systematic Evaluation of Predictive Fairness

Xudong Han, Aili Shen, Trevor Cohn +2

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, consideri…

cs.CL20224 cited

Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation

Thinh Hung Truong, Yulia Otmakhova, Timothy Baldwin +3

Negation is poorly captured by current language models, although the extent of this problem is not widely understood. We introduce a natural language inference (NLI) test suite to…

cs.CR2022

Detecting Backdoors in Deep Text Classifiers

You Guo, Jun Wang, Trevor Cohn

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour…

cs.CL20222 cited

LED down the rabbit hole: exploring the potential of global attention for biomedical multi-document summarisation

Yulia Otmakhova, Hung Thinh Truong, Timothy Baldwin +3

In this paper we report on our submission to the Multidocument Summarisation for Literature Review (MSLR) shared task. Specifically, we adapt PRIMERA (Xiao et al., 2022) to the bio…

cs.CL2022

Improving negation detection with negation-focused pre-training

Thinh Hung Truong, Timothy Baldwin, Trevor Cohn +1

Negation is a common linguistic feature that is crucial in many language understanding tasks, yet it remains a hard problem due to diversity in its expression in different types of…