ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models

Abstract

Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of text and graph leveraging Reinforcement Learning (RL) to improve performance. Graph linearization enables us to re-frame both tasks as a sequence to sequence generation problem regardless of the generative direction, which in turn allows the use of Reinforcement Learning for sequence training where the model itself is employed as its own critic leading to Self-Critical Sequence Training (SCST). We present an extensive investigation demonstrating that the use of RL via SCST benefits graph and text generation on WebNLG+ 2020 and TekGen datasets. Our system provides state-of-the-art results on WebNLG+ 2020 by significantly improving upon published results from the WebNLG 2020+ Challenge for both text-to-graph and graph-to-text generation tasks.

arXiv commentAccepted to appear in the main conference of EMNLP 2021

References in corpus (8)

• A Deep Reinforced Model for Abstractive Summarization
• Deep Reinforcement Learning for Dialogue Generation
• Reinforcement Learning Neural Turing Machines - Revised
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
• A Better Variant of Self-Critical Sequence Training
• Connecting the Dots Between MLE and RL for Sequence Prediction
• Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings