TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data
Fan Zhou, Mengkang Hu, Haoyu Dong, Zhoujun Cheng, Fan Cheng, Shi Han, Dongmei Zhang
摘要
Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks. However, auto-regressive PLMs are challenged by recent emerging numerical reasoning datasets, such as TAT-QA, due to the error-prone implicit calculation. In this paper, we present TaCube, to pre-compute aggregation/arithmetic results for the table in advance, so that they are handy and readily available for PLMs to answer numerical reasoning questions. TaCube systematically and comprehensively covers a collection of computational operations over table segments. By simply concatenating TaCube to the input sequence of PLMs, it shows significant experimental effectiveness. TaCube promotes the F1 score from 49.6% to 66.2% on TAT-QA and achieves new state-of-the-art results on Wik-iTQ (59.6% denotation accuracy). TaCube 's improvements on numerical reasoning cases are even more notable: on TAT-QA, TaCube promotes the exact match accuracy of BARTlarge by 39.6% on sum, 52.5% on average, 36.6% on substraction, and 22.2% on division. We believe that TaCube is a general and portable pre-computation solution that can be potentially integrated to various numerical reasoning frameworks. Data and code will be available at https://github.com/ koalazf99/tacube .
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 5 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- OpenTab: Advancing Large Language Models as Open-domain Table Reasoners 引用了 UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
- OpenTab: Advancing Large Language Models as Open-domain Table Reasoners 引用了 TAPEX: Table Pre-training via Learning a Neural SQL Executor
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models 引用了 TAPEX: Table Pre-training via Learning a Neural SQL Executor
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models 引用了 TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
- QTSumm: Query-Focused Summarization over Tabular Data 引用了 TabFact: A Large-scale Dataset for Table-based Fact Verification
- QTSumm: Query-Focused Summarization over Tabular Data 引用了 TAPEX: Table Pre-training via Learning a Neural SQL Executor
- QTSumm: Query-Focused Summarization over Tabular Data 引用了 MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data
- ReAcTable: Enhancing ReAct for Table Question Answering 引用了 TAPEX: Table Pre-training via Learning a Neural SQL Executor
- TAPEX: Table Pre-training via Learning a Neural SQL Executor 引用了 TabFact: A Large-scale Dataset for Table-based Fact Verification
- TAPEX: Table Pre-training via Learning a Neural SQL Executor 引用了 TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
- TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data 引用了 TabFact: A Large-scale Dataset for Table-based Fact Verification
- ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples 引用了 TabFact: A Large-scale Dataset for Table-based Fact Verification
- ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples 引用了 UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
- ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples 引用了 TAPEX: Table Pre-training via Learning a Neural SQL Executor
- ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples 引用了 TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
- ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples 引用了 MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data
- MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data 引用了 UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
引用它的顶会 Paper5
- ReAcTable: Enhancing ReAct for Table Question AnsweringYunjia Zhang, Jordan Henkel, Avrilia Floratou, Joyce Cahoon 等VLDB 2024 · 120 次引用
- OpenTab: Advancing Large Language Models as Open-domain Table ReasonersKezhi Kong, Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan 等ICLR 2024 · 40 次引用
- PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in FinanceYang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam 等EMNLP 2022 · 25 次引用
- ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning ExamplesYilun Zhao, Linyong Nan, Zhenting Qi, Rui Zhang 等EMNLP 2022 · 15 次引用
- QTSumm: Query-Focused Summarization over Tabular DataYilun Zhao, Zhenting Qi, Linyong Nan, Boyu Mi 等EMNLP 2023 · 4 次引用
它引用的 Paper11
- TabFact: A Large-scale Dataset for Table-based Fact VerificationWenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang 等ICLR 2020 · 674 次引用
- TaBERT: Pretraining for Joint Understanding of Textual and Tabular DataPengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian RiedelACL 2020 · 417 次引用
- TAPEX: Table Pre-training via Learning a Neural SQL ExecutorQian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi 等ICLR 2022 · 347 次引用
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language ModelsTianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong 等EMNLP 2022 · 222 次引用
- MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual DataYilun Zhao, Yunxiang Li, Chenying Li, Rui ZhangACL 2022 · 168 次引用
相关 Paper
- TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in FinanceFengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang 等ACL 2021
- TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular DataChangjiang Jiang, Fengchang Yu, Haihua Chen, Wei Lu 等EMNLP Findings 2025 · 3 次引用
- Injecting Numerical Reasoning Skills into Language ModelsMor Geva, Ankit Gupta, Jonathan BerantACL 2020 · 12 次引用
- TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model ReasoningYuan Sui, Jiaru Zou, Mengyu Zhou, Xinyi He 等EMNLP Findings 2024 · 18 次引用
- Evaluating LLMs' Mathematical Reasoning in Financial Document Question AnsweringPragya Srivastava, Manuj Malik, Vivek Gupta, Tanuja Ganu 等ACL Findings 2024 · 27 次引用
