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 …

Data-to-text generation has recently attracted substantial interests due to its wide
applications. Existing methods have shown impressive performance on an array of tasks …

Although neural table-to-text models have achieved remarkable progress with the help of
large-scale datasets, they suffer insufficient learning problem with limited training data …

Text generation from a knowledge base aims to translate knowledge triples to natural
language descriptions. Most existing methods ignore the faithfulness between a generated …

Abstract Data-to-Text Generation (DTG) is a subfield of Natural Language Generation
aiming at transcribing structured data in natural language descriptions. The field has been …

This paper studies how to automatically generate a natural language text that describes the
facts in knowledge graph (KG). Considering the few-shot setting, we leverage the excellent …

Transcribing structured data into natural language descriptions has emerged as a
challenging task, referred to as “data-to-text”. These structures generally regroup multiple …

Although Seq2Seq models for table-to-text generation have achieved remarkable progress,
modeling table representation in one dimension is inadequate. This is because (1) the table …

The neural boom that has sparked natural language processing (NLP) research throughout
the last decade has similarly led to significant innovations in data-to-text (D2T) generation …

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 …