Dialogue Meaning Representation for Task-Oriented Dialogue Systems
This addresses scalability issues in dialogue systems for developers and researchers, though it is incremental as it builds on hierarchical structures.
The authors tackled the problem of representing complex compositional semantics in task-oriented dialogues by proposing Dialogue Meaning Representation (DMR), a graph-based framework, and introduced a dataset with over 70k utterances, showing that DMR can be parsed effectively and their coreference resolution model outperforms baselines by a large margin.
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.