Abstract
We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search. It’s designed to enable researchers to use natural language queries to find precise answers and extract insights from a massive amount of academic papers. We present a large improvement over classic search engine baseline on several standard QA datasets and provide the community a collaborative data collection tool to curate the first natural language processing research QA dataset via a community effort.- Anthology ID:
- 2020.acl-demos.5
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Asli Celikyilmaz, Tsung-Hsien Wen
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 30–36
- Language:
- URL:
- https://aclanthology.org/2020.acl-demos.5
- DOI:
- 10.18653/v1/2020.acl-demos.5
- Cite (ACL):
- Tiancheng Zhao and Kyusong Lee. 2020. Talk to Papers: Bringing Neural Question Answering to Academic Search. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 30–36, Online. Association for Computational Linguistics.
- Cite (Informal):
- Talk to Papers: Bringing Neural Question Answering to Academic Search (Zhao & Lee, ACL 2020)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2020.acl-demos.5.pdf
- Data
- MS MARCO, Natural Questions, SQuAD