TY - GEN
T1 - SCITAT
T2 - 63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
AU - Zhang, Xuanliang
AU - Wang, Dingzirui
AU - Wang, Baoxin
AU - Dou, Longxu
AU - Lu, Xinyuan
AU - Xu, Keyan
AU - Wu, Dayong
AU - Zhu, Qingfu
AU - Che, Wanxiang
N1 - Publisher Copyright:
© 2025 Association for Computational Linguistics.
PY - 2025
Y1 - 2025
N2 - 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 reason on both tables and text, we require the questions to incorporate tables and text as much as possible. Based on SCITAT, we propose a 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 4.1% over other baselines on SCITAT, validating its effectiveness. Error analysis reveals the challenges of SCITAT, such as complex numerical calculations and domain knowledge.
AB - 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 reason on both tables and text, we require the questions to incorporate tables and text as much as possible. Based on SCITAT, we propose a 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 4.1% over other baselines on SCITAT, validating its effectiveness. Error analysis reveals the challenges of SCITAT, such as complex numerical calculations and domain knowledge.
UR - https://www.scopus.com/pages/publications/105028624631
U2 - 10.18653/v1/2025.findings-acl.199
DO - 10.18653/v1/2025.findings-acl.199
M3 - 会议稿件
AN - SCOPUS:105028624631
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 3859
EP - 3881
BT - Findings of the Association for Computational Linguistics
A2 - Che, Wanxiang
A2 - Nabende, Joyce
A2 - Shutova, Ekaterina
A2 - Pilehvar, Mohammad Taher
PB - Association for Computational Linguistics (ACL)
Y2 - 27 July 2025 through 1 August 2025
ER -