# Discourse Coherence, Reference Grounding and Goal Oriented Dialogue

arXiv: https://arxiv.org/abs/2007.04428 · HTML: https://mlsanity.com/paper/2007.04428/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 1 of 1)

- [Investigating Reinforcement Learning for Communication Strategies in a Task-Initiative Setting](https://mlsanity.com/paper/2308.01479/) (2023)

## Abstract (arXiv)

Prior approaches to realizing mixed-initiative human--computer referential communication have adopted information-state or collaborative problem-solving approaches. In this paper, we argue for a new approach, inspired by coherence-based models of discourse such as SDRT citeasher-lascarides:2003a, in which utterances attach to an evolving discourse structure and the associated knowledge graph of speaker commitments serves as an interface to real-world reasoning and conversational strategy. As first steps towards implementing the approach, we describe a simple dialogue system in a referential communication domain that accumulates constraints across discourse, interprets them using a learned probabilistic model, and plans clarification using reinforcement learning.