Talk to Papers: Bringing Neural Question Answering to Academic Search

2020/04/04 by Tianchang Zhao, Zhao, Tianchang, Kyusong Lee +1 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.CL

paper · pdf · doi:10.48550/arxiv.2004.02002

demo paper accepted at ACL 2020

openalex publication_date 2020/04/04 · arxiv created 2020/05/21 · arxiv updated 2020/05/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Building Watson: An Overview of the DeepQA Project
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Universal Sentence Encoder
• Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
• Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

Cited by

• TermSight: Making Service Contracts Approachable

Related

• Revisiting the Open-Domain Question Answering Pipeline
• A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
• PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR
• Scholarly Question Answering using Large Language Models in the NFDI4DataScience Gateway