English

Contrastive Triple Extraction with Generative Transformer

Computation and Language 2023-01-26 v8 Artificial Intelligence Databases Information Retrieval Machine Learning

Abstract

Triple extraction is an essential task in information extraction for natural language processing and knowledge graph construction. In this paper, we revisit the end-to-end triple extraction task for sequence generation. Since generative triple extraction may struggle to capture long-term dependencies and generate unfaithful triples, we introduce a novel model, contrastive triple extraction with a generative transformer. Specifically, we introduce a single shared transformer module for encoder-decoder-based generation. To generate faithful results, we propose a novel triplet contrastive training object. Moreover, we introduce two mechanisms to further improve model performance (i.e., batch-wise dynamic attention-masking and triple-wise calibration). Experimental results on three datasets (i.e., NYT, WebNLG, and MIE) show that our approach achieves better performance than that of baselines.

Keywords

Cite

@article{arxiv.2009.06207,
  title  = {Contrastive Triple Extraction with Generative Transformer},
  author = {Hongbin Ye and Ningyu Zhang and Shumin Deng and Mosha Chen and Chuanqi Tan and Fei Huang and Huajun Chen},
  journal= {arXiv preprint arXiv:2009.06207},
  year   = {2023}
}

Comments

Accepted by AAAI 2021

R2 v1 2026-06-23T18:30:43.100Z