no code implementations • EMNLP (MRQA) 2021 • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question–context lexical overlap.
1 code implementation • 29 Nov 2022 • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
We assume that the learnability of shortcuts, i. e., how easy it is to learn a shortcut, is useful to mitigate the problem.
no code implementations • 29 Nov 2022 • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Contrary to our expectations, although models become sensitive to the four types of perturbations, we find that the OOD generalization is not improved.
no code implementations • 26 Oct 2022 • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Specifically, we find that when the relative positions in a training set are biased, the performance on examples with relative positions unseen during training is significantly degraded.
no code implementations • 13 Oct 2021 • Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to interact with objects in 3D environments.
1 code implementation • 23 Sep 2021 • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question-context lexical overlap.
1 code implementation • ACL 2021 • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
While most existing QAG methods aim to improve the quality of synthetic examples, we conjecture that diversity-promoting QAG can mitigate the sparsity of training sets and lead to better robustness.
no code implementations • ACL 2019 • Kyosuke Nishida, Itsumi Saito, Kosuke Nishida, Kazutoshi Shinoda, Atsushi Otsuka, Hisako Asano, Junji Tomita
Second, whereas previous studies built a specific model for each answer style because of the difficulty of acquiring one general model, our approach learns multi-style answers within a model to improve the NLG capability for all styles involved.
Ranked #1 on Question Answering on MS MARCO