Understanding tables with intermediate pre-training

Julian Eisenschlos, Syrine Krichene, Thomas Müller


Abstract
Table entailment, the binary classification task of finding if a sentence is supported or refuted by the content of a table, requires parsing language and table structure as well as numerical and discrete reasoning. While there is extensive work on textual entailment, table entailment is less well studied. We adapt TAPAS (Herzig et al., 2020), a table-based BERT model, to recognize entailment. Motivated by the benefits of data augmentation, we create a balanced dataset of millions of automatically created training examples which are learned in an intermediate step prior to fine-tuning. This new data is not only useful for table entailment, but also for SQA (Iyyer et al., 2017), a sequential table QA task. To be able to use long examples as input of BERT models, we evaluate table pruning techniques as a pre-processing step to drastically improve the training and prediction efficiency at a moderate drop in accuracy. The different methods set the new state-of-the-art on the TabFact (Chen et al., 2020) and SQA datasets.
Anthology ID:
2020.findings-emnlp.27
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
281–296
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.27
DOI:
10.18653/v1/2020.findings-emnlp.27
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.27.pdf
Optional supplementary material:
 2020.findings-emnlp.27.OptionalSupplementaryMaterial.pdf
Video:
 https://slideslive.com/38940134