Enhancing AMR-to-Text Generation with Dual Graph Representations

By Leonardo F. R. Ribeiro, Claire Gardent, Iryna Gurevych. 2019

66 citations recorded by the source corpus.

Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges. To address this difficulty, we propose a novel graph-to-sequence model that encodes different but complementary perspectives of the structural information contained in the AMR graph. The model learns parallel top-down and bottom-up representations of nodes capturing contrasting views of the graph. We also investigate the use of different node message passing strategies, employing different state-of-the-art graph encoders to compute node representations based on incoming and outgoing perspectives. In our experiments, we demonstrate that the dual graph representation leads to improvements in AMR-to-text generation, achieving state-of-the-art results on two AMR datasets

Subfields: Artificial Intelligence, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, methodology): “…slot-value pairs, Abstract Meaning Representation (AMR) (Flanigan et al., 2016; Fer-reira et al., 2017; Song et al., 2017; Zhu et al., 2019a; Ribeiro et al., 2019; Damonte and Co-hen, 2019; Wang et al., 2020a; Zhao et al., 2020b; Shen et al., 2020), Minimal Recursion Semantics (MRS) (Hajdik…”
GPT-too: A Language-Model-First Approach for AMR-to-Text Generation (2020, result): “Table 4 shows human Evaluation results and semantic similarity scores of GPT-2L and GPT-2M compared to (Zhu et al., 2019; Ribeiro et al., 2019; Guo et al., 2019).”
Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity (2020, methodology): “In the LDC2017T10 dataset (Knight et al., 2017), D is an Abstract Meaning Representation (AMR) graph representing “who is doing what to whom” for each sentence in T .”
Investigating Pretrained Language Models for Graph-to-Text Generation (2020, methodology): “Recent approaches (Marcheggiani and Perez Bel-trachini, 2018; Song et al., 2018; Beck et al., 2018; Damonte and Cohen, 2019; Ribeiro et al., 2019; Zhao et al., 2020a; Schmitt et al., 2021; Ribeiro et al., 2021b) propose architectures based on GNNs to directly encode the graph structure, whereas…”
Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR (2020, background): “AMR-to-text generation is a task that has garnered lots of attention over the recent years (Song et al., 2017, 2018; Konstas et al., 2017; Cai and Lam, 2020b; Ribeiro et al., 2019).”
A Human Evaluation of AMR-to-English Generation Systems (2020, methodology): “In particular, Ribeiro et al. (2019) conducted a Mechanical Turk evaluation to compare their best graph encoder model with a sequence-to-sequence baseline, ﬁnding that their model performs better on both meaning similarity between the generated sentence and the gold reference, and readability of…”
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs (2020, background): “C L ] 2 9 Ja n 20 20 on Graph Neural Networks (GNN) (Ribeiro et al., 2019; Guo et al., 2019) and (ii) models that leverage global node aggregation.”
Structural Information Preserving for Graph-to-Text Generation (2020, methodology): “Taking AMR-to-text generation as an example, different graph neural networks (GNNs) (Beck et al., 2018; Song et al., 2018; Guo et al., 2019; Ribeiro et al., 2019) have been introduced to better represent input AMRs than a sequence-to-sequence model (Konstas et al., 2017), and later work (Zhu et…”