Academic Reader: An Interactive Question Answering System on Academic Literatures
Abstract
We present Academic Reader, a system which can read academic literatures and answer the relevant questions for researchers. Academic Reader leverages machine reading comprehension technique, which has been successfully applied in many fields but has not been involved in academic literature reading. An interactive platform is established to demonstrate the functions of Academic Reader. Pieces of academic literature and relevant questions are input to our system, which then outputs answers. The system can also gather users’ revised answers and perform active learning to continuously improve its performance. A case study is provided presenting the performance of our system on all papers accepted in KDD 2018, which demonstrates how our system facilitates massive academic literature reading.
Cite
Text
Hong et al. "Academic Reader: An Interactive Question Answering System on Academic Literatures." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019855Markdown
[Hong et al. "Academic Reader: An Interactive Question Answering System on Academic Literatures." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/hong2019aaai-academic/) doi:10.1609/AAAI.V33I01.33019855BibTeX
@inproceedings{hong2019aaai-academic,
title = {{Academic Reader: An Interactive Question Answering System on Academic Literatures}},
author = {Hong, Yining and Wang, Jialu and Jia, Yuting and Zhang, Weinan and Wang, Xinbing},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2019},
pages = {9855-9856},
doi = {10.1609/AAAI.V33I01.33019855},
url = {https://mlanthology.org/aaai/2019/hong2019aaai-academic/}
}