Talk to Papers: Bringing Neural Question Answering to Academic Search
This addresses the challenge for researchers in efficiently extracting insights from vast academic literature, though it is incremental as it applies existing QA techniques to a new domain.
The paper tackles the problem of academic search by introducing Talk to Papers, a system that uses neural question answering to allow researchers to query papers with natural language, resulting in large improvements over classic search engines on standard QA datasets.
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.