Dialogue Meaning Representation for Task-Oriented Dialogue Systems

TL;DR

This paper introduces Dialogue Meaning Representation (DMR), a flexible, hierarchical semantic framework for task-oriented dialogues, along with a new annotated dataset and models for coreference resolution, improving expressiveness and parsing accuracy.

Contribution

The paper presents DMR, a novel extendable semantic representation with hierarchical structure, and provides a new dataset and models to enhance dialogue understanding and coreference resolution.

Findings

DMR can be effectively parsed by pre-trained Seq2Seq models.

GNNCoref significantly outperforms baseline coreference models.

The annotated DMR-FastFood dataset contains over 70,000 utterances.

Abstract

Dialogue meaning representation formulates natural language utterance semantics in their conversational context in an explicit and machine-readable form. Previous work typically follows the intent-slot framework, which is easy for annotation yet limited in scalability for complex linguistic expressions. A line of works alleviates the representation issue by introducing hierarchical structures but challenging to express complex compositional semantics, such as negation and coreference. We propose Dialogue Meaning Representation (DMR), a pliable and easily extendable representation for task-oriented dialogue. Our representation contains a set of nodes and edges to represent rich compositional semantics. Moreover, we propose an inheritance hierarchy mechanism focusing on domain extensibility. Additionally, we annotated DMR-FastFood, a multi-turn dialogue dataset with more than 70k utterances, with DMR. We propose two evaluation tasks to evaluate different dialogue models and a novel coreference resolution model GNNCoref for the graph-based coreference resolution task. Experiments show that DMR can be parsed well with pre-trained Seq2Seq models, and GNNCoref outperforms the baseline models by a large margin.