SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xuanliang, Wang, Dingzirui, Wang, Baoxin, Dou, Longxu, Lu, Xinyuan, Xu, Keyan, Wu, Dayong, Zhu, Qingfu, Che, Wanxiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912158890065920
author Zhang, Xuanliang
Wang, Dingzirui
Wang, Baoxin
Dou, Longxu
Lu, Xinyuan
Xu, Keyan
Wu, Dayong
Zhu, Qingfu
Che, Wanxiang
author_facet Zhang, Xuanliang
Wang, Dingzirui
Wang, Baoxin
Dou, Longxu
Lu, Xinyuan
Xu, Keyan
Wu, Dayong
Zhu, Qingfu
Che, Wanxiang
contents Scientific question answering (SQA) is an important task aimed at answering questions based on papers. However, current SQA datasets have limited reasoning types and neglect the relevance between tables and text, creating a significant gap with real scenarios. To address these challenges, we propose a QA benchmark for scientific tables and text with diverse reasoning types (SciTaT). To cover more reasoning types, we summarize various reasoning types from real-world questions. To involve both tables and text, we require the questions to incorporate tables and text as much as possible. Based on SciTaT, we propose a strong baseline (CaR), which combines various reasoning methods to address different reasoning types and process tables and text at the same time. CaR brings average improvements of 12.9% over other baselines on SciTaT, validating its effectiveness. Error analysis reveals the challenges of SciTaT, such as complex numerical calculations and domain knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11757
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types
Zhang, Xuanliang
Wang, Dingzirui
Wang, Baoxin
Dou, Longxu
Lu, Xinyuan
Xu, Keyan
Wu, Dayong
Zhu, Qingfu
Che, Wanxiang
Computation and Language
Scientific question answering (SQA) is an important task aimed at answering questions based on papers. However, current SQA datasets have limited reasoning types and neglect the relevance between tables and text, creating a significant gap with real scenarios. To address these challenges, we propose a QA benchmark for scientific tables and text with diverse reasoning types (SciTaT). To cover more reasoning types, we summarize various reasoning types from real-world questions. To involve both tables and text, we require the questions to incorporate tables and text as much as possible. Based on SciTaT, we propose a strong baseline (CaR), which combines various reasoning methods to address different reasoning types and process tables and text at the same time. CaR brings average improvements of 12.9% over other baselines on SciTaT, validating its effectiveness. Error analysis reveals the challenges of SciTaT, such as complex numerical calculations and domain knowledge.
title SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types
topic Computation and Language
url https://arxiv.org/abs/2412.11757