Data-to-text Generation (D2T) aims to generate textual natural language statements that can
fluently and precisely describe the structured data such as graphs, tables, and meaning …

The ability to convey relevant and faithful information is critical for many tasks in conditional
generation and yet remains elusive for neural seq-to-seq models whose outputs often reveal …

Generating sequential natural language descriptions from graph-structured data (eg,
knowledge graph) is challenging, partly because of the structural differences between the …

End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to
pipeline-based architectures. However, it has faced challenges in generalizing to new …

In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data
representation and repeating training data noise. We examine how to avoid finetuning …

We consider the task of data-to-text generation, which aims to create textual output from non-
linguistic input. We focus on generating long-form text, that is, documents with multiple …

Prefix-tuning is a powerful lightweight technique for adapting a large pre-trained language
model to a downstream application. However, it uses the same dataset-level tuned prompt …

In open domain table-to-text generation, we notice the unfaithful generation usually contains
hallucinated entities which can not be aligned to any input table record. We thus try to …

We present a novel approach to data-to-text generation based on iterative text editing. Our
approach maximizes the completeness and semantic accuracy of the output text while …

We study the degree to which neural sequence-to-sequence models exhibit fine-grained
controllability when performing natural language generation from a meaning representation …