Diversity Enhanced Table-to-Text Generation via Type Control
This work addresses the need for diverse outputs in table-to-text generation, which is incremental as it builds on existing methods by incorporating type control.
The paper tackled the problem of generating diverse natural language statements from tabular data by proposing a type-controlled model, achieving superior quality and factuality-diversity trade-off compared to strong baselines in evaluations on two Logical NLG datasets.
Generating natural language statements to convey logical inferences from tabular data (i.e., Logical NLG) is a process with one input and a variety of valid outputs. This characteristic underscores the need for a method to produce a diverse set of valid outputs, presenting different perspectives of the input data. We propose a simple yet effective diversity-enhancing scheme that builds upon an inherent property of the statements, their logic-types, by using a type-controlled table-to-text generation model. We demonstrate, through extensive automatic and human evaluations over the two publicly available Logical NLG datasets, that our proposed method both facilitates the ability to effectively control the generated statement type, and produces results superior to the strongest baselines in terms of quality and factuality-diversity trade-off.