TABBIE: Pretrained Representations of Tabular Data

Hiroshi Iida, Dung Thai, Varun Manjunatha, Mohit Iyyer


Abstract
Existing work on tabular representation-learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT. While this joint pretraining improves tasks involving paired tables and text (e.g., answering questions about tables), we show that it underperforms on tasks that operate over tables without any associated text (e.g., populating missing cells). We devise a simple pretraining objective (corrupt cell detection) that learns exclusively from tabular data and reaches the state-of-the-art on a suite of table-based prediction tasks. Unlike competing approaches, our model (TABBIE) provides embeddings of all table substructures (cells, rows, and columns), and it also requires far less compute to train. A qualitative analysis of our model’s learned cell, column, and row representations shows that it understands complex table semantics and numerical trends.
Anthology ID:
2021.naacl-main.270
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3446–3456
Language:
URL:
https://aclanthology.org/2021.naacl-main.270
DOI:
10.18653/v1/2021.naacl-main.270
Bibkey:
Cite (ACL):
Hiroshi Iida, Dung Thai, Varun Manjunatha, and Mohit Iyyer. 2021. TABBIE: Pretrained Representations of Tabular Data. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3446–3456, Online. Association for Computational Linguistics.
Cite (Informal):
TABBIE: Pretrained Representations of Tabular Data (Iida et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2021.naacl-main.270.pdf
Video:
 https://preview.aclanthology.org/auto-file-uploads/2021.naacl-main.270.mp4
Code
 SFIG611/tabbie
Data
VizNet-Sato