Lune

ACL Findings2023

A Diffusion Model for Event Skeleton Generation

Fangqi Zhu, Lin Zhang, Jun Gao, Bing Qin, Ruifeng Xu, Haiqin Yang

Abstract

Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task. Existing methods effectively address this task from a graph generation perspective but suffer from noise-sensitive and error accumulation, e.g., the inability to correct errors while generating schema. We, therefore, propose a novel Diffusion Event Graph Model (DEGM) to address these issues. Our DEGM is the first workable diffusion model for event skeleton generation, where the embedding and rounding techniques with a custom edge-based loss are introduced to transform a discrete event graph into learnable latent representation. Furthermore, we propose a denoising training process to maintain the model's robustness. Consequently, DEGM derives the final schema, where error correction is guaranteed by iteratively refining the latent representation during the schema generation process. Experimental results on three IED bombing datasets demonstrate that our DEGM achieves better results than other stateof-the-art baselines. Our code and data are available at https://github.com/zhufq00/ EventSkeletonGeneration.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding cites The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction
  • Learning to Describe for Predicting Zero-shot Drug-Drug Interactions cites A Generative Approach for Script Event Prediction via Contrastive Fine-Tuning
  • The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction cites Connecting the Dots: Event Graph Schema Induction with Path Language Modeling
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Learning to Describe for Predicting Zero-shot Drug-Drug InteractionsFangqi Zhu, Yongqi Zhang, Lei Chen, Bing Qin et al.EMNLP 2023 · 10 citations
  2. Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context UnderstandingZhihan Zhang, Yixin Cao, Chenchen Ye, Yunshan Ma et al.ACL 2024

Builds on7

  1. Diffusion-LM Improves Controllable Text GenerationXiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang et al.NeurIPS 2022 · 1,546 citations
  2. NodeFormer: A Scalable Graph Structure Learning Transformer for Node ClassificationQitian Wu, Wentao Zhao, Zenan Li, David P. Wipf et al.NeurIPS 2022 · 472 citations
  3. Connecting the Dots: Event Graph Schema Induction with Path Language ModelingManling Li, Qi Zeng, Ying Lin, Kyunghyun Cho et al.EMNLP 2020 · 71 citations
  4. The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event PredictionManling Li, Sha Li, Zhenhailong Wang, Lifu Huang et al.EMNLP 2021 · 29 citations
  5. A Generative Approach for Script Event Prediction via Contrastive Fine-TuningFangqi Zhu, Jun Gao, Changlong Yu, Wei Wang et al.AAAI 2023 · 22 citations

Related papers

  1. Complex Event Schema Induction with Knowledge-Enriched Diffusion ModelYupu Hao, Pengfei Cao, Yubo Chen, Kang Liu et al.EMNLP Findings 2023 · 4 citations
  2. Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and VerificationSha Li, Ruining Zhao, Manling Li, Heng Ji et al.ACL 2023 · 14 citations
  3. KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph EmbeddingXiao Long, Liansheng Zhuang, Aodi Li, Jiuchang Wei et al.AAAI 2024 · 16 citations
  4. Graph Generation with Diffusion MixtureJaehyeong Jo, Dongki Kim, Sung Ju HwangICML 2024 · 49 citations
  5. Unifying Generation and Prediction on Graphs with Latent Graph DiffusionCai Zhou, Xiyuan Wang, Muhan ZhangNeurIPS 2024 · 37 citations
Dusk over the sea between two cliffs drawn in fine vertical lines