# Neural Language Modeling for Contextualized Temporal Graph Generation

arXiv: https://arxiv.org/abs/2010.10077 · HTML: https://mlsanity.com/paper/2010.10077/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2020.

## Built on by (most cited first, 13 of 13)

- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [proScript: Partially Ordered Scripts Generation via Pre-trained Language Models](https://mlsanity.com/paper/2104.08251/) (2021)
- [Think about it! Improving defeasible reasoning by first modeling the question scenario](https://mlsanity.com/paper/2110.12349/) (2021)
- [Could you give me a hint? Generating inference graphs for defeasible reasoning](https://mlsanity.com/paper/2105.05418/) (2021)
- [Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning](https://mlsanity.com/paper/2204.04813/) (2022)
- [Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation](https://mlsanity.com/paper/2404.01532/) (2024)
- [Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering](https://mlsanity.com/paper/2310.19292/) (2023)
- [Cascading Large Language Models for Salient Event Graph Generation](https://mlsanity.com/paper/2406.18449/) (2024)
- [FLOWGEN: Fast and slow graph generation](https://mlsanity.com/paper/2207.07656/) (2022)
- [EventFull: Complete and Consistent Event Relation Annotation](https://mlsanity.com/paper/2412.12733/) (2024)
- [Explanation Graph Generation via Generative Pre-training over Synthetic Graphs](https://mlsanity.com/paper/2306.00652/) (2023)
- [Causal schema induction for knowledge discovery](https://mlsanity.com/paper/2303.15381/) (2023)

## Abstract (arXiv)

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. Despite the huge success of neural pre-training methods in NLP tasks, its potential for temporal reasoning over event graphs has not been sufficiently explored. Part of the reason is the difficulty in obtaining large training corpora with human-annotated events and temporal links. We address this challenge by using existing IE/NLP tools to automatically generate a large quantity (89,000) of system-produced document-graph pairs, and propose a novel formulation of the contextualized graph generation problem as a sequence-to-sequence mapping task. These strategies enable us to leverage and fine-tune pre-trained language models on the system-induced training data for the graph generation task. Our experiments show that our approach is highly effective in generating structurally and semantically valid graphs. Further, evaluation on a challenging hand-labeled, out-domain corpus shows that our method outperforms the closest existing method by a large margin on several metrics. Code and pre-trained models are available at https://github.com/madaan/temporal-graph-gen.