Speech and Natural Language Processing > Question Answering
The science of asking and answering in natural language with a machine.
Contents
Recent Trends
paper: https://arxiv.org/pdf/2010.08422.pdf
paper: https://arxiv.org/pdf/2005.00038.pdf
Demo: https://unifiedqa.apps.allenai.org/
paper: https://arxiv.org/pdf/1910.01108.pdf, Victor sanh, et al., arXiv, 2019.
Recent QA Models
Recent Language Models
, Kevin Clark, et al., ICLR, 2020.
, Xiaoqi Jiao, et al., ICLR, 2020.
, Wenhui Wang, et al., arXiv, 2020.
, Colin Raffel, et al., arXiv preprint, 2019.
, Zhengyan Zhang, et al., ACL, 2019.
, Zhilin Yang, et al., arXiv preprint, 2019.
, Zhenzhong Lan, et al., arXiv preprint, 2019.
, Yinhan Liu, et al., arXiv preprint, 2019.
, Victor sanh, et al., arXiv, 2019.
, Mandar Joshi, et al., TACL, 2019.
ACL 2019
, Mark Hopkins, et al., ACL-W 2019, Jun 2019.
, Wei Zhao, et al., ACL 2019, Jun 2019.
, Ming Ding, et al., ACL 2019, Jun 2019.
, Minjoon Seo, et al., ACL 2019, Jun 2019.
, Patrick Lewis, et al., ACL 2019, Jun 2019.
, Wenhan Xiong, et al., ACL 2019, May 2019.
, Bang Liu, et al., ACL 2019, May 2019.
, Moonsu Han, et al., ACL 2019, Mar 2019.
, Tom Kwiatkowski, et al., TACL 2019, Jan 2019.
, Daesik Kim, et al., ACL 2019, Nov 2018.
Codes
A new language representation model which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers.
Bi-Directional Attention Flow (BIDAF) network is a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.
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.
An end-to-end neural networks model for reading comprehension style question answering, which aims to answer questions from a given passage.
R-NET re-implementation in Keras.
DrQA is a system for reading comprehension applied to open-domain question answering.
Publications
Dataset Collections
Datasets
Hermann et al. (2015) created two awesome datasets using news articles for Q&A research. Each dataset contains many documents (90k and 197k each), and each document companies on average 4 questions approximately. Each question is a sentence with one missing word/phrase which can be found from the accompanying document/context.
On generating Characteristic-rich Question sets for QA evaluation.
It includes the list of documents with Wikipedia summaries, links to full stories, and questions and answers.
A machine comprehension dataset
MS Research's publication within 5 years
Samira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, Akos Kadar, Adam Trischler, Yoshua Bengio, ICLR, 2018
Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman, RepL4NLP, 2016.
Yi Yang, Wen-tau Yih, and Christopher Meek, EMNLP, 2015.
Samira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, Akos Kadar, Adam Trischler, Yoshua Bengio, ICLR, 2018
Zichao Yang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Smola, CVPR, 2016.
Yih, Scott Wen-tau and Ma, Hao, ACM SIGIR, 2016.
Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman, RepL4NLP, 2016.
Sun, Huan and Ma, Hao and He, Xiaodong and Yih, Wen-tau and Su, Yu and Yan, Xifeng, WWW, 2016.
Chen-Tse Tsai, Wen-tau Yih, and Christopher J.C. Burges, MSR-TR, 2015.
Huan Sun, Hao Ma, Wen-tau Yih, Chen-Tse Tsai, Jingjing Liu, and Ming-Wei Chang, WWW, 2015.
Zhenghao Wang, Shengquan Yan, Huaming Wang, and Xuedong Huang, MSR-TR, 2014.