A Graph-to-Sequence Model for AMR-to-Text Generation

TL;DR

This paper introduces a neural graph-to-sequence model for AMR-to-text generation that directly encodes graph semantics, outperforming sequence-based models especially on large graphs.

Contribution

The paper proposes a novel LSTM-based graph encoding method that preserves graph structure, improving over traditional sequence-to-sequence approaches.

Findings

Achieves superior results on standard benchmarks

Handles large graphs more effectively

Outperforms existing sequence-based models

Abstract

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. Although being able to model non-local semantic information, a sequence LSTM can lose information from the AMR graph structure, and thus faces challenges with large graphs, which result in long sequences. We introduce a neural graph-to-sequence model, using a novel LSTM structure for directly encoding graph-level semantics. On a standard benchmark, our model shows superior results to existing methods in the literature.