# From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?

arXiv: https://arxiv.org/abs/2305.10568 · HTML: https://mlsanity.com/paper/2305.10568/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [SemEval-2013 Task 4: Free Paraphrases of Noun Compounds](https://mlsanity.com/paper/1911.10421/) (2019)
- [Will it Unblend?](https://mlsanity.com/paper/2009.09123/) (2020)
- [NYTWIT: A Dataset of Novel Words in the New York Times](https://mlsanity.com/paper/2003.03444/) (2020)
- [Systematicity in GPT-3's Interpretation of Novel English Noun Compounds](https://mlsanity.com/paper/2210.09492/) (2022)
- [Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations](https://mlsanity.com/paper/1805.02442/) (2018)
- [Learning to Predict Novel Noun-Noun Compounds](https://mlsanity.com/paper/1906.03634/) (2019)
- [Large-Scale Noun Compound Interpretation Using Bootstrapping and the Web as a Corpus](https://mlsanity.com/paper/1911.12085/) (2019)

## Built on by (most cited first, 12 of 12)

- [Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context](https://mlsanity.com/paper/2410.16069/) (2024)
- [Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs](https://mlsanity.com/paper/2502.13195/) (2025)
- [Semantics of Multiword Expressions in Transformer-Based Models: A Survey](https://mlsanity.com/paper/2401.15393/) (2024)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [Memorization or Reasoning? Exploring the Idiom Understanding of LLMs](https://mlsanity.com/paper/2505.16216/) (2025)
- [Do Vision-Language Models Understand Compound Nouns?](https://mlsanity.com/paper/2404.00419/) (2024)
- [Is artificial intelligence still intelligence? LLMs generalize to novel adjective-noun pairs, but don't mimic the full human distribution](https://mlsanity.com/paper/2410.17482/) (2024)
- [Is a Peeled Apple Still Red? Evaluating LLMs' Ability for Conceptual Combination with Property Type](https://mlsanity.com/paper/2502.06086/) (2025)
- [How do Transformer Embeddings Represent Compositions? A Functional Analysis](https://mlsanity.com/paper/2506.00914/) (2025)
- [A Comparative Approach to Assessing Linguistic Creativity of Large Language Models and Humans](https://mlsanity.com/paper/2507.12039/) (2025)
- [Willkommens-Merkel, Chaos-Johnson, and Tore-Klose: Modeling the Evaluative Meaning of German Personal Name Compounds](https://mlsanity.com/paper/2404.04031/) (2024)
- [Probing BERT for German Compound Semantics](https://mlsanity.com/paper/2505.14130/) (2025)

## Abstract (arXiv)

Noun compound interpretation is the task of expressing a noun compound (e.g. chocolate bunny) in a free-text paraphrase that makes the relationship between the constituent nouns explicit (e.g. bunny-shaped chocolate). We propose modifications to the data and evaluation setup of the standard task (Hendrickx et al., 2013), and show that GPT-3 solves it almost perfectly. We then investigate the task of noun compound conceptualization, i.e. paraphrasing a novel or rare noun compound. E.g., chocolate crocodile is a crocodile-shaped chocolate. This task requires creativity, commonsense, and the ability to generalize knowledge about similar concepts. While GPT-3's performance is not perfect, it is better than that of humans -- likely thanks to its access to vast amounts of knowledge, and because conceptual processing is effortful for people (Connell and Lynott, 2012). Finally, we estimate the extent to which GPT-3 is reasoning about the world vs. parroting its training data. We find that the outputs from GPT-3 often have significant overlap with a large web corpus, but that the parroting strategy is less beneficial for novel noun compounds.