OmniTab:使用自然和合成数据进行预训练,用于几次基于表格的问答

Zhengbao Jiang, Yi Mao, Pengcheng He, Graham Neubig, Weizhu Chen
{"title":"OmniTab:使用自然和合成数据进行预训练,用于几次基于表格的问答","authors":"Zhengbao Jiang, Yi Mao, Pengcheng He, Graham Neubig, Weizhu Chen","doi":"10.48550/arXiv.2207.03637","DOIUrl":null,"url":null,"abstract":"The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables often adds an extra burden to both model design and data annotation. In this paper, we aim to develop a simple table-based QA model with minimal annotation effort. Motivated by the fact that table-based QA requires both alignment between questions and tables and the ability to perform complicated reasoning over multiple table elements, we propose an omnivorous pretraining approach that consumes both natural and synthetic data to endow models with these respective abilities. Specifically, given freely available tables, we leverage retrieval to pair them with relevant natural sentences for mask-based pretraining, and synthesize NL questions by converting SQL sampled from tables for pretraining with a QA loss. We perform extensive experiments in both few-shot and full settings, and the results clearly demonstrate the superiority of our model OmniTab, with the best multitasking approach achieving an absolute gain of 16.2% and 2.7% in 128-shot and full settings respectively, also establishing a new state-of-the-art on WikiTableQuestions. Detailed ablations and analyses reveal different characteristics of natural and synthetic data, shedding light on future directions in omnivorous pretraining.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"284 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"24","resultStr":"{\"title\":\"OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering\",\"authors\":\"Zhengbao Jiang, Yi Mao, Pengcheng He, Graham Neubig, Weizhu Chen\",\"doi\":\"10.48550/arXiv.2207.03637\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables often adds an extra burden to both model design and data annotation. In this paper, we aim to develop a simple table-based QA model with minimal annotation effort. Motivated by the fact that table-based QA requires both alignment between questions and tables and the ability to perform complicated reasoning over multiple table elements, we propose an omnivorous pretraining approach that consumes both natural and synthetic data to endow models with these respective abilities. Specifically, given freely available tables, we leverage retrieval to pair them with relevant natural sentences for mask-based pretraining, and synthesize NL questions by converting SQL sampled from tables for pretraining with a QA loss. We perform extensive experiments in both few-shot and full settings, and the results clearly demonstrate the superiority of our model OmniTab, with the best multitasking approach achieving an absolute gain of 16.2% and 2.7% in 128-shot and full settings respectively, also establishing a new state-of-the-art on WikiTableQuestions. Detailed ablations and analyses reveal different characteristics of natural and synthetic data, shedding light on future directions in omnivorous pretraining.\",\"PeriodicalId\":382084,\"journal\":{\"name\":\"North American Chapter of the Association for Computational Linguistics\",\"volume\":\"284 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"24\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"North American Chapter of the Association for Computational Linguistics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2207.03637\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"North American Chapter of the Association for Computational Linguistics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2207.03637","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 24

摘要

表格中的信息可以作为文本的重要补充,使基于表格的问答(QA)系统具有很大的价值。处理表固有的复杂性通常会给模型设计和数据注释增加额外的负担。在本文中,我们的目标是用最少的注释工作开发一个简单的基于表的QA模型。基于表的QA既需要问题和表之间的一致性,也需要对多个表元素执行复杂推理的能力,因此我们提出了一种杂食性的预训练方法,它使用自然数据和合成数据来赋予模型这些各自的能力。具体来说,给定免费可用的表,我们利用检索将它们与相关的自然句子配对进行基于掩码的预训练,并通过转换从表中采样的SQL进行预训练来合成NL问题。我们在少镜头和全镜头设置下进行了大量的实验,结果清楚地证明了我们的模型OmniTab的优越性,最佳的多任务处理方法在128镜头和全镜头设置下分别获得了16.2%和2.7%的绝对增益,同时也在WikiTableQuestions上建立了新的技术水平。详细的消融和分析揭示了自然数据和合成数据的不同特征,为杂食性预训练的未来方向指明了方向。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering
The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables often adds an extra burden to both model design and data annotation. In this paper, we aim to develop a simple table-based QA model with minimal annotation effort. Motivated by the fact that table-based QA requires both alignment between questions and tables and the ability to perform complicated reasoning over multiple table elements, we propose an omnivorous pretraining approach that consumes both natural and synthetic data to endow models with these respective abilities. Specifically, given freely available tables, we leverage retrieval to pair them with relevant natural sentences for mask-based pretraining, and synthesize NL questions by converting SQL sampled from tables for pretraining with a QA loss. We perform extensive experiments in both few-shot and full settings, and the results clearly demonstrate the superiority of our model OmniTab, with the best multitasking approach achieving an absolute gain of 16.2% and 2.7% in 128-shot and full settings respectively, also establishing a new state-of-the-art on WikiTableQuestions. Detailed ablations and analyses reveal different characteristics of natural and synthetic data, shedding light on future directions in omnivorous pretraining.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信