INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion

• URL: http://arxiv.org/abs/2209.10754v1
• Date: Thu, 22 Sep 2022 03:12:43 GMT
• Title: INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion
• Authors: Yi Xu, Luoyi Fu, Zhouhan Lin, Jiexing Qi, Xinbing Wang
• Abstract summary: Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are essential tasks for constructing and applying knowledge graphs. Existing unsupervised approaches turn out to be suitable candidates for jointly learning the two tasks due to their avoidance of using graph-text parallel data. We propose INFINITY, a simple yet effective unsupervised approach that does not require external annotation tools or additional parallel information.
• Score: 43.70416280548082
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for constructing and applying knowledge graphs. Existing unsupervised approaches turn out to be suitable candidates for jointly learning the two tasks due to their avoidance of using graph-text parallel data. However, they are composed of multiple modules and still require both entity information and relation type in the training process. To this end, we propose INFINITY, a simple yet effective unsupervised approach that does not require external annotation tools or additional parallel information. It achieves fully unsupervised graph-text mutual conversion for the first time. Specifically, INFINITY treats both G2T and T2G as a bidirectional sequence generation task by fine-tuning only one pretrained seq2seq model. A novel back-translation-based framework is then designed to automatically generate continuous synthetic parallel data. To obtain reasonable graph sequences with structural information from source texts, INFINITY employs reward-based training loss by leveraging the advantage of reward augmented maximum likelihood. As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks.

Related papers

• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Self-supervised Graph Masking Pre-training for Graph-to-Text Generation [5.108327983929205]
  Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation. We propose graph masking pre-training strategies that neither require supervision signals nor adjust the architecture of the underlying pre-trained encoder-decoder model. Our approach achieves new state-of-the-art results on WebNLG+ 2020 and EventNarrative G2T generation datasets.
  arXiv  Detail & Related papers  (2022-10-19T14:44:56Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• A multi-task semi-supervised framework for Text2Graph & Graph2Text [2.2344764434954256]
  We jointly learn graph extraction from text and text generation from graphs. Our approach surpasses unsupervised state-of-the-art results in text-to-graph and graph-to-text. The resulting model can be easily trained in any new domain with non-parallel data.
  arXiv  Detail & Related papers  (2022-02-12T11:02:17Z)
• Training Free Graph Neural Networks for Graph Matching [103.45755859119035]
  TFGM is a framework to boost the performance of Graph Neural Networks (GNNs) based graph matching without training. Applying TFGM on various GNNs shows promising improvements over baselines.
  arXiv  Detail & Related papers  (2022-01-14T09:04:46Z)
• CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training [63.11444020743543]
  Deep learning models for graph-to-text (G2T) and text-to-graph (T2G) conversion suffer from scarce training data. We present CycleGT, an unsupervised training method that can bootstrap from non-parallel graph and text data, and iteratively back translate between the two forms.
  arXiv  Detail & Related papers  (2020-06-08T15:59:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.