aveni-ai/aveni-bench-tat-qa

--- license: mit language: - en configs: - config_name: aveni-bench-tat-qa data_files: - split: valid path: - data/valid.jsonl - split: test path: - data/test.jsonl default: true tags: - aveni-bench - tabular-reasoning - numerical-reasoning - finnlp --- # AveniBench: TAT-QA TAT-QA split used in the AveniBench. ## License This dataset is made available under the MIT license. ## Citation AveniBench ```bibtex TDB ``` TAT-QA ```bibtex @inproceedings{zhu-etal-2021-tat, title = "{TAT}-{QA}: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance", author = "Zhu, Fengbin and Lei, Wenqiang and Huang, Youcheng and Wang, Chao and Zhang, Shuo and Lv, Jiancheng and Feng, Fuli and Chua, Tat-Seng", booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.acl-long.254/", doi = "10.18653/v1/2021.acl-long.254", pages = "3277--3287", } ```AveniBench: TAT-QA is a question answering benchmark on a hybrid of tabular and textual content in finance. It includes validation and test sets to evaluate the performance of models in tabular reasoning and numerical reasoning.

搜集汇总

背景与挑战

背景概述

该数据集是AveniBench中使用的TAT-QA子集，专注于金融领域的表格和文本混合问答任务，包含约3300个样本，用于表格推理和数值推理评估。