DeepAI AI Chat
Log In Sign Up

Stage-wise Fine-tuning for Graph-to-Text Generation

by   Qingyun Wang, et al.

Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.


page 2

page 8

page 9


Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods

It has been a common approach to pre-train a language model on a large c...

GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation

Recent improvements in KG-to-text generation are due to additional auxil...

Faithful Low-Resource Data-to-Text Generation through Cycle Training

Methods to generate text from structured data have advanced significantl...

Discourse-Aware Prompt Design for Text Generation

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, et...

Distilling the Knowledge of BERT for Text Generation

Large-scale pre-trained language model, such as BERT, has recently achie...

DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation

Self-training (ST) has prospered again in language understanding by augm...

Relational Memory Augmented Language Models

We present a memory-augmented approach to condition an autoregressive la...