Pengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian Riedel
Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks. Such models are typically trained on free-form NL text, hence may not be suitable for tasks like semantic parsing over structured data, which require reasoning over both free-form NL questions and structured tabular data (e.g., database tables). In this paper we present TaBERT, a pretrained LM that jointly learns representations for NL sentences and (semi-)structured tables. TaBERT is trained on a large corpus of 26 million tables and their English contexts. In experiments, neural semantic parsers using TaBERT as feature representation layers achieve new best results on the challenging weakly-supervised semantic parsing benchmark WikiTableQuestions, while performing competitively on the text-to-SQL dataset Spider. Implementation of the model will be available at http://fburl.com/TaBERT .
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Semantic Parsing | WikiTableQuestions | Accuracy (Dev) | 52.2 | MAPO + TABERTLarge (K = 3) |
| Semantic Parsing | WikiTableQuestions | Accuracy (Test) | 51.8 | MAPO + TABERTLarge (K = 3) |
| Semantic Parsing | spider | Exact Match Accuracy (Dev) | 64.5 | MAPO + TABERTLarge (K = 3) |
| Text-To-SQL | spider | Exact Match Accuracy (Dev) | 64.5 | MAPO + TABERTLarge (K = 3) |