# Talk to Papers: Bringing Neural Question Answering to Academic Search

arXiv: https://arxiv.org/abs/2004.02002 · HTML: https://mlsanity.com/paper/2004.02002/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing](https://mlsanity.com/paper/2203.00130/) (2022)
- [The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces](https://mlsanity.com/paper/2303.14334/) (2023)
- [Steering AI-Driven Personalization of Scientific Text for General Audiences](https://mlsanity.com/paper/2411.09969/) (2024)
- [Detect, Retrieve, Comprehend: A Flexible Framework for Zero-Shot Document-Level Question Answering](https://mlsanity.com/paper/2210.01959/) (2022)
- [GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions](https://mlsanity.com/paper/2206.08441/) (2022)

## Abstract (arXiv)

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.