# Decomposing and Recomposing Event Structure

arXiv: https://arxiv.org/abs/2103.10387 · HTML: https://mlsanity.com/paper/2103.10387/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 70 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 10 of 10)

- ["Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding](https://mlsanity.com/paper/1909.03065/) (2019)
- [Joint Constrained Learning for Event-Event Relation Extraction](https://mlsanity.com/paper/2010.06727/) (2020)
- [Temporal Common Sense Acquisition with Minimal Supervision](https://mlsanity.com/paper/2005.04304/) (2020)
- [Fine-Grained Temporal Relation Extraction](https://mlsanity.com/paper/1902.01390/) (2019)
- [Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements](https://mlsanity.com/paper/1901.11429/) (2019)
- [The Universal Decompositional Semantics Dataset and Decomp Toolkit](https://mlsanity.com/paper/1909.13851/) (2019)
- [Neural-Davidsonian Semantic Proto-role Labeling](https://mlsanity.com/paper/1804.07976/) (2018)
- [Natural Language Inference with Mixed Effects](https://mlsanity.com/paper/2010.10501/) (2020)
- [Universal Decompositional Semantic Parsing](https://mlsanity.com/paper/1910.10138/) (2019)
- [A Broad-Coverage Deep Semantic Lexicon for Verbs](https://mlsanity.com/paper/2007.02670/) (2020)

## Built on by (most cited first, 5 of 5)

- [A Kind Introduction to Lexical and Grammatical Aspect, with a Survey of Computational Approaches](https://mlsanity.com/paper/2208.09012/) (2022)
- [Argument Linking: A Survey and Forecast](https://mlsanity.com/paper/2107.08523/) (2021)
- [On Event Individuation for Document-Level Information Extraction](https://mlsanity.com/paper/2212.09702/) (2022)
- [The Case for Scalable, Data-Driven Theory: A Paradigm for Scientific Progress in NLP](https://mlsanity.com/paper/2312.00349/) (2023)
- [Enhancing Structured Meaning Representations with Aspect Classification](https://mlsanity.com/paper/2603.24797/) (2026)

## Abstract (arXiv)

We present an event structure classification empirically derived from inferential properties annotated on sentence- and document-level Universal Decompositional Semantics (UDS) graphs. We induce this classification jointly with semantic role, entity, and event-event relation classifications using a document-level generative model structured by these graphs. To support this induction, we augment existing annotations found in the UDS1.0 dataset, which covers the entirety of the English Web Treebank, with an array of inferential properties capturing fine-grained aspects of the temporal and aspectual structure of events. The resulting dataset (available at decomp.io) is the largest annotation of event structure and (partial) event coreference to date.