Improving Graph-to-Text Generation Using Cycle Training

Natural Language Generation (NLG) from
graph structured data is an important step for
a number of tasks, including e.g. generating
explanations, automated reporting, and conver-
sational interfaces. Large generative language
models are currently the state of the art for open
ended NLG for graph data. However, these
models can produce erroneous text (termed hal-
lucinations). In this paper, we investigate the
application of cycle training in order to reduce
these errors. Cycle training involves alternating
the generation of text from an input graph with
the extraction of a knowledge graph where the
model should ensure consistency between the
extracted graph and the input graph. Our results
show that cycle training improves performance
on evaluation metrics (e.g., METEOR, DAE)
that consider syntactic and semantic relations,
and more in generally, that cycle training is use-
ful to reduce erroneous output when generating
text from graphs.