arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.01785cs.DBcs.CL
收藏

使用预训练的语言模型注释列

Annotating Columns with Pre-trained Language Models

Megagon Labs(Megagon实验室);Sigma Computing(Sigma计算公司);Meta AI

Yoshihiko Suhara, Jinfeng Li, Yuliang Li, Dan Zhang, Çağatay Demiralp, Chen Chen, Wang-Chiew Tan

摘要:

在数据管理中,推断有关表的Meta信息(如列标题或列之间的关系)是一个活跃的研究主题,因为我们发现许多表缺少某些此类信息。在本文中,我们研究了注释表列的问题(即,预测列类型和列之间的关系)。我们开发了一个基于预训练的语言模型的多任务学习框架(称为Doduo),该框架将整个表作为输入,并使用单个模型预测列类型/关系。实验结果表明,Doduo在列类型预测和列关系预测任务的两个基准测试中建立了新的最先进的性能,分别提高了4.0%和11.9%。我们报告说,Doduo已经可以用最少数量的令牌(每列只有8个令牌)来超越以前最先进的性能。我们发布了一个工具箱(https://github.com/megagonlabs/doduo),并通过案例研究证实了Doduo在现实世界的数据科学问题上的有效性。

英文摘要:

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results show that Doduo establishes new state-of-the-art performance on two benchmarks for the column type prediction and column relation prediction tasks with up to 4.0% and 11.9% improvements, respectively. We report that Doduo can already outperform the previous state-of-the-art performance with a minimal number of tokens, only 8 tokens per column. We release a toolbox (https://github.com/megagonlabs/doduo) and confirm the effectiveness of Doduo on a real-world data science problem through a case study.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑