# Representation of Constituents in Neural Language Models: Coordination Phrase as a Case Study

arXiv: https://arxiv.org/abs/1909.04625 · HTML: https://mlsanity.com/paper/1909.04625/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models](https://mlsanity.com/paper/2401.14440/) (2024)
- [Different types of syntactic agreement recruit the same units within large language models](https://mlsanity.com/paper/2512.03676/) (2025)
- [Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models](https://mlsanity.com/paper/2109.11058/) (2021)
- [Investigating grammatical abstraction in language models using few-shot learning of novel noun gender](https://mlsanity.com/paper/2403.10338/) (2024)

## Abstract (arXiv)

Neural language models have achieved state-of-the-art performances on many NLP tasks, and recently have been shown to learn a number of hierarchically-sensitive syntactic dependencies between individual words. However, equally important for language processing is the ability to combine words into phrasal constituents, and use constituent-level features to drive downstream expectations. Here we investigate neural models' ability to represent constituent-level features, using coordinated noun phrases as a case study. We assess whether different neural language models trained on English and French represent phrase-level number and gender features, and use those features to drive downstream expectations. Our results suggest that models use a linear combination of NP constituent number to drive CoordNP/verb number agreement. This behavior is highly regular and even sensitive to local syntactic context, however it differs crucially from observed human behavior. Models have less success with gender agreement. Models trained on large corpora perform best, and there is no obvious advantage for models trained using explicit syntactic supervision.