Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management

Milan Gritta,Ignacio Iacobacci,Gerasimos Lampouras

doi:10.1162/tacl_a_00352

Abstract

Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of the dialogues. Additionally, conventional training signal in- ference is not suitable for non-deterministic agent behavior, namely, considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4%.

Highlights

Dialogue systems research focuses on the natural language interaction between a user and an artificial conversational agent
We show that augmentation with ConvGraph leads to improvements of up to 6.4% when applied in an end-toend dialogue system
We have introduced the Conversation Graph for Dialogue Management, an approach that unifies conversations based on matching nodes

Summary

Introduction

Dialogue systems research focuses on the natural language interaction between a user and an artificial conversational agent. Reinforcement learning approaches (Henderson et al, 2008; Bordes et al, 2017; Miller et al, 2017; Li et al, 2017; Gordon-Hall et al, 2020) can replace the need for explicit training data by exploiting a custom-designed environment to infer the training signal for the policy Such custom-designed environments may not be representative of how a user would interact with a conversational agent and their manual development is time-consuming and domain-specific. Related to our work is a recent paper on MultiAction Data Augmentation (MADA; Zhang et al, 2019) To us, they are leveraging the fact that a non-deterministic agent can take different actions given the same dialogue state. MADA does not consider any dialogue history, this approach is not suitable for dialogue management data augmentation

Methods

Results

Conclusion