Table-to-Text Natural Language Generation with Unseen Schemas
This addresses a generalization challenge in NLG for real-world scenarios with infinite schemas, though it is incremental as it builds on existing table-to-text methods.
The paper tackles the problem of table-to-text natural language generation for unseen schemas, where input tables have attribute types not present during training, and proposes a model that aligns unseen schemas to seen ones and generates text, outperforming baselines by a large margin on a new benchmark dataset.
Traditional table-to-text natural language generation (NLG) tasks focus on generating text from schemas that are already seen in the training set. This limitation curbs their generalizabilities towards real-world scenarios, where the schemas of input tables are potentially infinite. In this paper, we propose the new task of table-to-text NLG with unseen schemas, which specifically aims to test the generalization of NLG for input tables with attribute types that never appear during training. To do this, we construct a new benchmark dataset for this task. To deal with the problem of unseen attribute types, we propose a new model that first aligns unseen table schemas to seen ones, and then generates text with updated table representations. Experimental evaluation on the new benchmark demonstrates that our model outperforms baseline methods by a large margin. In addition, comparison with standard data-to-text settings shows the challenges and uniqueness of our proposed task.