Beyond Pairwise: Global Zero-shot Temporal Graph Generation

• URL: http://arxiv.org/abs/2502.11114v1
• Date: Sun, 16 Feb 2025 13:06:50 GMT
• Title: Beyond Pairwise: Global Zero-shot Temporal Graph Generation
• Authors: Alon Eirew, Kfir Bar, Ido Dagan,
• Abstract summary: Temporal relation extraction (TRE) is a fundamental task in natural language processing (NLP) We propose a novel zero-shot method for TRE that generates a document's complete temporal graph at once. We also introduce OmniTemp, a new dataset with complete annotations for all pairs of targeted events within a document.
• Score: 18.054145230023884
• License:
• Abstract: Temporal relation extraction (TRE) is a fundamental task in natural language processing (NLP) that involves identifying the temporal relationships between events in a document. Despite the advances in large language models (LLMs), their application to TRE remains limited. Most existing approaches rely on pairwise classification, in which event pairs are considered individually, leading to computational inefficiency and a lack of global consistency in the resulting temporal graph. In this work, we propose a novel zero-shot method for TRE that generates a document's complete temporal graph at once, then applies transitive constraints optimization to refine predictions and enforce temporal consistency across relations. Additionally, we introduce OmniTemp, a new dataset with complete annotations for all pairs of targeted events within a document. Through experiments and analyses, we demonstrate that our method significantly outperforms existing zero-shot approaches while achieving competitive performance with supervised models.

Related papers

• LAST SToP For Modeling Asynchronous Time Series [19.401463051705377]
  We present a novel prompt design for Large Language Models (LLMs) tailored to Asynchronous Time Series. Our approach effectively utilizes the rich natural language of event descriptions, allowing LLMs to benefit from their broad world knowledge for reasoning across different domains and tasks. We further introduce Soft Prompting, a novel prompt-tuning mechanism that significantly improves model performance, outperforming existing fine-tuning methods such as QLoRA.
  arXiv  Detail & Related papers  (2025-02-04T01:42:45Z)
• EventFull: Complete and Consistent Event Relation Annotation [16.089136332919487]
  textitEventFull is a tool that supports consistent, complete and efficient annotation of temporal, causal and coreference relations. A pilot study demonstrates that EventFull accelerates and simplifies the annotation process while yielding high inter-annotator agreement.
  arXiv  Detail & Related papers  (2024-12-17T09:55:41Z)
• IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphs [8.861995276194435]
  This paper addresses domain adaptation challenges in graph data resulting from chronological splits. We propose IMPaCT, a method that imposes invariant properties based on realistic assumptions derived from temporal graph structures. We show that IMPaCT achieves a 3.8% performance improvement over current SOTA method on the ogbn-mag graph dataset.
  arXiv  Detail & Related papers  (2024-11-17T04:23:25Z)
• Localizing Factual Inconsistencies in Attributable Text Generation [91.981439746404]
  We introduce QASemConsistency, a new formalism for localizing factual inconsistencies in attributable text generation. We first demonstrate the effectiveness of the QASemConsistency methodology for human annotation. We then implement several methods for automatically detecting localized factual inconsistencies.
  arXiv  Detail & Related papers  (2024-10-09T22:53:48Z)
• A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models [20.220781775335645]
  We introduce a Condensed Transition Graph Framework for Zero-Shot Link Prediction (CTLP) CTLP encodes all the paths' information in linear time complexity to predict unseen relations between entities. Our proposed CTLP method achieves state-of-the-art performance on three standard ZSLP datasets.
  arXiv  Detail & Related papers  (2024-02-16T16:02:33Z)
• TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
  TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
  arXiv  Detail & Related papers  (2024-01-06T06:26:49Z)
• More than Classification: A Unified Framework for Event Temporal Relation Extraction [61.44799147458621]
  Event temporal relation extraction(ETRE) is usually formulated as a multi-label classification task. We observe that all relations can be interpreted using the start and end time points of events. We propose a unified event temporal relation extraction framework, which transforms temporal relations into logical expressions of time points.
  arXiv  Detail & Related papers  (2023-05-28T02:09:08Z)
• Taming Local Effects in Graph-based Spatiotemporal Forecasting [28.30604130617646]
  Stemporal graph neural networks have shown to be effective in time series forecasting applications. This paper aims to understand the interplay between globality and locality in graph-basedtemporal forecasting. We propose a methodological framework to rationalize the practice of including trainable node embeddings in such architectures.
  arXiv  Detail & Related papers  (2023-02-08T14:18:56Z)
• CEP3: Community Event Prediction with Neural Point Process on Graph [59.434777403325604]
  We propose a novel model combining Graph Neural Networks and Marked Temporal Point Process (MTPP) Our experiments demonstrate the superior performance of our model in terms of both model accuracy and training efficiency.
  arXiv  Detail & Related papers  (2022-05-21T15:30:25Z)
• One-shot Learning for Temporal Knowledge Graphs [49.41854171118697]
  We propose a one-shot learning framework for link prediction in temporal knowledge graphs. Our proposed method employs a self-attention mechanism to effectively encode temporal interactions between entities. Our experiments show that the proposed algorithm outperforms the state of the art baselines for two well-studied benchmarks.
  arXiv  Detail & Related papers  (2020-10-23T03:24:44Z)
• Neural Language Modeling for Contextualized Temporal Graph Generation [49.21890450444187]
  This paper presents the first study on using large-scale pre-trained language models for automated generation of an event-level temporal graph for a document.
  arXiv  Detail & Related papers  (2020-10-20T07:08:00Z)

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.