4 papers
AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions
Son Quoc Tran, Gia-Huy Do, Phong Nguyen-Thuan Do +2
The development of large high-quality datasets and high-performing models have led to significant advancements in the domain of Extractive Question Answering (EQA). This progress h…
Single-Sentence Reader: A Novel Approach for Addressing Answer Position Bias
Son Quoc Tran, Matt Kretchmar
Machine Reading Comprehension (MRC) models tend to take advantage of spurious correlations (also known as dataset bias or annotation artifacts in the research community). Consequen…
Revealing Weaknesses of Vietnamese Language Models Through Unanswerable Questions in Machine Reading Comprehension
Son Quoc Tran, Phong Nguyen-Thuan Do, Kiet Van Nguyen +1
Although the curse of multilinguality significantly restricts the language abilities of multilingual models in monolingual settings, researchers now still have to rely on multiling…
The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models
Son Quoc Tran, Phong Nguyen-Thuan Do, Uyen Le +1
Pretrained language models have achieved super-human performances on many Machine Reading Comprehension (MRC) benchmarks. Nevertheless, their relative inability to defend against a…