# Improving Event Duration Prediction via Time-aware Pre-training

arXiv: https://arxiv.org/abs/2011.02610 · HTML: https://mlsanity.com/paper/2011.02610/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

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

- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses](https://mlsanity.com/paper/2410.07076/) (2024)
- [Language Models as Inductive Reasoners](https://mlsanity.com/paper/2212.10923/) (2022)
- [Mitigating Temporal Misalignment by Discarding Outdated Facts](https://mlsanity.com/paper/2305.14824/) (2023)
- [Salient Span Masking for Temporal Understanding](https://mlsanity.com/paper/2303.12860/) (2023)
- [It's High Time: A Survey of Temporal Question Answering](https://mlsanity.com/paper/2505.20243/) (2025)
- [Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering](https://mlsanity.com/paper/2410.04752/) (2024)
- [An Overview Of Temporal Commonsense Reasoning and Acquisition](https://mlsanity.com/paper/2308.00002/) (2023)
- [A Kind Introduction to Lexical and Grammatical Aspect, with a Survey of Computational Approaches](https://mlsanity.com/paper/2208.09012/) (2022)
- [Temporal Validity Change Prediction](https://mlsanity.com/paper/2401.00779/) (2024)
- [AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA](https://mlsanity.com/paper/2403.18504/) (2024)
- [How often do Answers Change? Estimating Recency Requirements in Question Answering](https://mlsanity.com/paper/2603.16544/) (2026)

## Abstract (arXiv)

End-to-end models in NLP rarely encode external world knowledge about length of time. We introduce two effective models for duration prediction, which incorporate external knowledge by reading temporal-related news sentences (time-aware pre-training). Specifically, one model predicts the range/unit where the duration value falls in (R-pred); and the other predicts the exact duration value E-pred. Our best model -- E-pred, substantially outperforms previous work, and captures duration information more accurately than R-pred. We also demonstrate our models are capable of duration prediction in the unsupervised setting, outperforming the baselines.