CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
This addresses the challenge of limited labeled data for knowledge graph and NLP tasks, offering a practical solution for researchers and practitioners in these fields, though it is incremental as it builds on cycle training concepts.
The paper tackles the data scarcity problem in graph-to-text and text-to-graph conversion by proposing CycleGT, an unsupervised training method that uses non-parallel data and iterative back translation, achieving performance on par with supervised models on WebNLG datasets and outperforming unsupervised baselines on GenWiki.
Two important tasks at the intersection of knowledge graphs and natural language processing are graph-to-text (G2T) and text-to-graph (T2G) conversion. Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG~2017 dataset after preprocessing, which is far fewer than the millions of data for other tasks such as machine translation. Consequently, deep learning models for G2T and T2G suffer largely from scarce training data. We present CycleGT, an unsupervised training method that can bootstrap from fully non-parallel graph and text data, and iteratively back translate between the two forms. Experiments on WebNLG datasets show that our unsupervised model trained on the same number of data achieves performance on par with several fully supervised models. Further experiments on the non-parallel GenWiki dataset verify that our method performs the best among unsupervised baselines. This validates our framework as an effective approach to overcome the data scarcity problem in the fields of G2T and T2G. Our code is available at https://github.com/QipengGuo/CycleGT.