CycleGT：通过循环训练的无监督图到文本和文本到图生成
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
摘要：
知识图谱和自然语言处理交叉的两个重要任务是图到文本（G2 T）和文本到图（T2 G）转换。由于数据汇集的难度和高成本，这两个领域可用的监督数据通常在数万量级，例如预处理后的WebNLG~2017数据集为18 K，远远少于机器翻译等其他任务的数百万数据。因此，G2 T和T2 G的深度学习模型在很大程度上受到缺乏训练数据的影响。我们提出了CycleGT，这是一种无监督的训练方法，可以从完全非并行的图形和文本数据中引导，并在两种形式之间迭代反向转换。在WebNLG数据集上的实验表明，我们在相同数量的数据上训练的无监督模型的性能与几个完全监督模型相当。在非并行GenWiki数据集上的进一步实验验证了我们的方法在无监督基线中表现最好。这验证了我们的框架是克服G2 T和T2 G领域数据稀缺问题的有效方法。我们的代码可在https://github.com/QipengGuo/CycleGT上获得。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
