Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings

TL;DR

This paper introduces a neural model with dynamic knowledge graph embeddings for symmetric collaborative dialogue, effectively capturing evolving knowledge and improving goal achievement and human-likeness.

Contribution

It presents a novel neural approach using dynamic knowledge graph embeddings for symmetric dialogue with private knowledge, supported by a new dataset of 11K dialogues.

Findings

Model outperforms baselines in goal achievement

Model generates more human-like dialogues

Effective modeling of evolving knowledge graphs

Abstract

We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses. Automatic and human evaluations show that our model is both more effective at achieving the goal and more human-like than baseline neural and rule-based models.