# Construction Repetition Reduces Information Rate in Dialogue

arXiv: https://arxiv.org/abs/2210.08321 · HTML: https://mlsanity.com/paper/2210.08321/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 84 references that are in the map.
- First posted on arXiv 15 Oct 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Dynamic Evaluation of Neural Sequence Models](https://mlsanity.com/paper/1709.07432/) (2017)
- [Human Sentence Processing: Recurrence or Attention?](https://mlsanity.com/paper/2005.09471/) (2020)
- [A Neural Model of Adaptation in Reading](https://mlsanity.com/paper/1808.09930/) (2018)
- [Taming Repetition in Dialogue Generation](https://mlsanity.com/paper/2112.08657/) (2021)

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

- [Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse](https://mlsanity.com/paper/2410.16062/) (2024)
- [On the Proper Treatment of Tokenization in Psycholinguistics](https://mlsanity.com/paper/2410.02691/) (2024)
- [Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue](https://mlsanity.com/paper/2311.13061/) (2023)
- [Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue](https://mlsanity.com/paper/2605.00506/) (2026)
- [Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation](https://mlsanity.com/paper/2609.04484/) (2026)

## Abstract (arXiv)

Speakers repeat constructions frequently in dialogue. Due to their peculiar information-theoretic properties, repetitions can be thought of as a strategy for cost-effective communication. In this study, we focus on the repetition of lexicalised constructions -- i.e., recurring multi-word units -- in English open-domain spoken dialogues. We hypothesise that speakers use construction repetition to mitigate information rate, leading to an overall decrease in utterance information content over the course of a dialogue. We conduct a quantitative analysis, measuring the information content of constructions and that of their containing utterances, estimating information content with an adaptive neural language model. We observe that construction usage lowers the information content of utterances. This facilitating effect (i) increases throughout dialogues, (ii) is boosted by repetition, (iii) grows as a function of repetition frequency and density, and (iv) is stronger for repetitions of referential constructions.