Semantic Representation for Dialogue Modeling

TL;DR

This paper introduces a novel approach using Abstract Meaning Representation (AMR) to enhance neural dialogue systems by explicitly capturing core semantics, leading to improved understanding and response generation.

Contribution

It is the first to incorporate formal semantic AMR graphs into neural dialogue modeling, improving semantic representation and system performance.

Findings

AMR improves dialogue understanding accuracy

AMR enhances response generation quality

Proposed method outperforms baseline models

Abstract

Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR) to help dialogue modeling. Compared with the textual input, AMR explicitly provides core semantic knowledge and reduces data sparsity. We develop an algorithm to construct dialogue-level AMR graphs from sentence-level AMRs and explore two ways to incorporate AMRs into dialogue systems. Experimental results on both dialogue understanding and response generation tasks show the superiority of our model. To our knowledge, we are the first to leverage a formal semantic representation into neural dialogue modeling.