Table-To-Text generation and pre-training with TabT5

10/17/2022
by   Ewa Andrejczuk, et al.
0

Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TABT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TABT5 overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings and pre-training. TABT5 achieves new state-of-the-art results on several domains, including spreadsheet formula prediction with a 15 increase in sequence accuracy, QA with a 2.5 data-to-text generation with a 2.5

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset