"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension"
, Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le, ICLR, 2018.
- from
- Question Answering
- added
- 2026-10-10
- likes
- 0
similar
-
QANet github.com
A Q&A architecture does not require recurrent networks: Its encoder consists exclusively of convolution and self-attention, where convolution models local interactions and self-attention models global interactions.
-
"NewsQA: A Machine Comprehension Dataset" arxiv.org
, Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman, RepL4NLP, 2016.
-
T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arxiv.org
, Colin Raffel, et al., arXiv preprint, 2019.
-
SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering arxiv.org
, Chenguang Zhu, et al., arXiv, Dec 2018.
-
Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications arxiv.org
, Wei Zhao, et al., ACL 2019, Jun 2019.
-
"Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors" arxiv.org
, Radu Soricut, Nan Ding, 2018.
Question Answering › Datasets > Google AI's publication within 5 years: “, Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le, ICLR, 2018.”