Table-To-Text generation and pre-training with TabT5
Autor: | Andrejczuk, Ewa, Eisenschlos, Julian Martin, Piccinno, Francesco, Krichene, Syrine, Altun, Yasemin |
---|---|
Rok vydání: | 2022 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | 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% increase in sequence accuracy and data-to-text generation with a 2.5% increase in BLEU. Comment: Accepted to Findings of EMNLP 2022 |
Databáze: | arXiv |
Externí odkaz: |