# Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements

arXiv: https://arxiv.org/abs/1901.11429 · HTML: https://mlsanity.com/paper/1901.11429/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2019.

## Built on by (most cited first, 10 of 10)

- [Holmes: A Benchmark to Assess the Linguistic Competence of Language Models](https://mlsanity.com/paper/2404.18923/) (2024)
- [Did they answer? Subjective acts and intents in conversational discourse](https://mlsanity.com/paper/2104.04470/) (2021)
- [Decomposing and Recomposing Event Structure](https://mlsanity.com/paper/2103.10387/) (2021)
- [A Kind Introduction to Lexical and Grammatical Aspect, with a Survey of Computational Approaches](https://mlsanity.com/paper/2208.09012/) (2022)
- [Discriminative and Generative Transformer-based Models For Situation Entity Classification](https://mlsanity.com/paper/2109.07434/) (2021)
- [Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm](https://mlsanity.com/paper/2307.13424/) (2023)
- [A Novel Corpus of Discourse Structure in Humans and Computers](https://mlsanity.com/paper/2111.05940/) (2021)
- [Specifying Genericity through Inclusiveness and Abstractness Continuous Scales](https://mlsanity.com/paper/2403.15278/) (2024)
- [Multimodal QUD: Inquisitive Questions from Scientific Figures](https://mlsanity.com/paper/2604.23733/) (2026)
- [How broad is that claim? Mapping Generalisation in NLP Research](https://mlsanity.com/paper/2609.14770/) (2026)

## Abstract (arXiv)

We present a novel semantic framework for modeling linguistic expressions of generalization---generic, habitual, and episodic statements---as combinations of simple, real-valued referential properties of predicates and their arguments. We use this framework to construct a dataset covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to probe the efficacy of type-level and token-level information---including hand-engineered features and static (GloVe) and contextual (ELMo) word embeddings---for predicting expressions of generalization. Data and code are available at decomp.io.