Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints
This addresses the issue of generating inaccurate or hallucinated text from tables, which is crucial for applications like automated reporting and data summarization, representing a strong specific gain in the domain.
The paper tackles the problem of unfaithful text generation from knowledge base tables by proposing a Transformer-based framework with content-matching constraints, achieving significant improvements over state-of-the-art methods as shown in evaluations.
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. Furthermore, to evaluate faithfulness, we propose a new automatic metric specialized to the table-to-text generation problem. We also provide detailed analysis on each component of our model in our experiments. Automatic and human evaluations show that our framework can significantly outperform state-of-the-art by a large margin.