CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

Abstract

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.

arXiv commentINLG 2020 Workshop

References in corpus (10)

• BERTScore: Evaluating Text Generation with BERT
• Style Transfer from Non-Parallel Text by Cross-Alignment
• Dual Learning for Machine Translation
• Relation Classification via Recurrent Neural Network
• Trainable Methods for Surface Natural Language Generation
• Pointing the Unknown Words
• When Does Unsupervised Machine Translation Work?
• A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation
• Relation of the Relations: A New Paradigm of the Relation Extraction Problem
• Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings

Cited by in corpus (8)

• Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers
• Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models
• Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
• Graphine: A Dataset for Graph-aware Terminology Definition Generation
• ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models
• JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
• Learning from Multiple Sources for Data-to-Text and Text-to-Data
• Generating Faithful Text From a Knowledge Graph with Noisy Reference Text