Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints

Understand

Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions.

• Most existing methods ignore the faithfulness between a generated text description and the original table, leading to generated information that goes beyond the content of the table.
• In this paper, for the first time, we propose a novel Transformer-based generation framework to achieve the goal.
• The core techniques in our method to enforce faithfulness include a new table-text optimal-transport matching loss and a table-text embedding similarity loss based on the Transformer model.