# GSN: A Graph-Structured Network for Multi-Party Dialogues

## TL;DR

This paper introduces GSN, a graph-structured neural network that effectively models multi-party dialogues by capturing parallel interactions, outperforming traditional sequence-based models.

## Contribution

It presents a novel graph-structured neural network for multi-party dialogue modeling, extending beyond sequential assumptions.

## Key findings

- GSN significantly outperforms sequence-based models
- Effective modeling of parallel interactions in multi-party dialogues
- Graph-structured encoder captures complex dialogue flows

## Abstract

Existing neural models for dialogue response generation assume that utterances are sequentially organized. However, many real-world dialogues involve multiple interlocutors (i.e., multi-party dialogues), where the assumption does not hold as utterances from different interlocutors can occur "in parallel." This paper generalizes existing sequence-based models to a Graph-Structured neural Network (GSN) for dialogue modeling. The core of GSN is a graph-based encoder that can model the information flow along the graph-structured dialogues (two-party sequential dialogues are a special case). Experimental results show that GSN significantly outperforms existing sequence-based models.