2021/04/30 by Yoshihiko Suhara, Jinfeng Li, Yuliang Li +4 · 70 citations
Computer Science · Decision Sciences · #Advanced Text Analysis Techniques #Artificial intelligence #Column (typography) #Computer science #Data Quality and Management #Data mining #Machine learning #Natural language processing #Programming language #Relation (database) #Table (database) #Task (project management) #Toolbox #Topic Modeling #cs.CL #cs.DB
paper · pdf · doi:10.1145/3514221.3517906
published in Proceedings of the 2022 International Conference on Management of Data, 1493-1503 · SIGMOD 2022
arxiv created 2022/03/01 · arxiv updated 2022/03/02 · openalex publication_date 2022/06/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.