DeepAI AI Chat
Log In Sign Up

Table-to-Text Natural Language Generation with Unseen Schemas

by   Tianyu Liu, et al.
Peking University
The Regents of the University of California

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.


page 1

page 2

page 3

page 4


PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation

Logical table-to-text generation is a task that involves generating logi...

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

Text generation from a knowledge base aims to translate knowledge triple...

Table-To-Text generation and pre-training with TabT5

Encoder-only transformer models have been successfully applied to differ...

Text-to-Table: A New Way of Information Extraction

We study a new problem setting of information extraction (IE), referred ...

Tabling Optimization for Contextual Abduction

Tabling for contextual abduction in logic programming has been introduce...

Tab2KG: Semantic Table Interpretation with Lightweight Semantic Profiles

Tabular data plays an essential role in many data analytics and machine ...

Optimizing Organizations for Navigating Data Lakes

Navigation is known to be an effective complement to search. In addition...