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

05/17/2021
by   Qingyun Wang, et al.
10

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.

READ FULL TEXT

page 2

page 8

page 9

research
07/13/2020

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...
research
04/13/2022

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...
research
08/12/2023

Generating Faithful Text From a Knowledge Graph with Noisy Reference Text

Knowledge Graph (KG)-to-Text generation aims at generating fluent natura...
research
08/10/2023

Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning

We present a novel approach for structured data-to-text generation that ...
research
05/24/2023

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

Methods to generate text from structured data have advanced significantl...
research
12/10/2021

Discourse-Aware Prompt Design for Text Generation

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, et...
research
11/10/2019

Distilling the Knowledge of BERT for Text Generation

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

Please sign up or login with your details

Forgot password? Click here to reset