Enhancing AMR-to-Text Generation with Dual Graph Representations

Ribeiro, Leonardo F. R.; Gardent, Claire; Gurevych, Iryna

doi:10.18653/v1/d19-1314

Cited by 46 publications

(49 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parameter Saving Strategy. (Ribeiro et al, 2019). Results are statistically significant with p < 0.05.…”

Section: Development Experimentsmentioning

confidence: 82%

“…We consider two kinds of baseline models: 1) models based on Recurrent Neural Networks (Konstas et al, 2017;Cao and Clark, 2019) and Graph Neural Networks (GNNs) (Song et al, 2018;Beck et al, 2018;Damonte and Cohen, 2019;Guo et al, 2019b;Ribeiro et al, 2019). These models use an attention-based LSTM decoder.…”

Section: Resultsmentioning

confidence: 99%

“…Early efforts (Pourdamghani et al, 2016;Konstas et al, 2017) neglect a significant part of the structural information in the input graph by linearizing it. Recently, Graph Neural Networks (GNNs) have been explored to better encode structural information for this task (Beck et al, 2018;Song et al, 2018;Damonte and Cohen, 2019;Ribeiro et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation

Zhang¹,

Guo²,

Teng³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

AMR-to-text generation is used to transduce Abstract Meaning Representation structures (AMR) into text. A key challenge in this task is to efficiently learn effective graph representations. Previously, Graph Convolution Networks (GCNs) were used to encode input AMRs, however, vanilla GCNs are not able to capture non-local information and additionally, they follow a local (first-order) information aggregation scheme. To account for these issues, larger and deeper GCN models are required to capture more complex interactions. In this paper, we introduce a dynamic fusion mechanism, proposing Lightweight Dynamic Graph Convolutional Networks (LDGCNs) that capture richer non-local interactions by synthesizing higher order information from the input graphs. We further develop two novel parameter saving strategies based on the group graph convolutions and weight tied convolutions to reduce memory usage and model complexity. With the help of these strategies, we are able to train a model with fewer parameters while maintaining the model capacity. Experiments demonstrate that LDGCNs outperform stateof-the-art models on two benchmark datasets for AMR-to-text generation with significantly fewer parameters. * * Equally Contributed. Work done while Yan Zhang was an intern at DAMO Academy, Alibaba Group and Zhijiang Guo was at the University of Edinburgh.

show abstract

“…Parameter Saving Strategy. (Ribeiro et al, 2019). Results are statistically significant with p < 0.05.…”

Section: Development Experimentsmentioning

confidence: 82%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation

Zhang¹,

Guo²,

Teng³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Initial work on AMR-to-text generation adapted methods from statistical machine translation (MT) (Pourdamghani et al, 2016), grammar-based generation (Mille et al, 2017), tree-to-string transducers (Flanigan et al, 2016), and inverted semantic parsing (Lampouras and Vlachos, 2017). Neural approaches explored sequence-to-sequence models where the AMR is linearized (Konstas et al, 2017) or modeled with a graph encoder (Marcheggiani and Perez-Beltrachini, 2018;Damonte and Cohen, 2019;Ribeiro et al, 2019;Song et al, 2018;Zhu et al, 2019). As professionally-annotated AMR datasets are in English, all this work focuses on English.…”

Section: Related Workmentioning

confidence: 99%

Multilingual AMR-to-Text Generation

Fan¹,

Gardent²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

Generating text from structured data is challenging because it requires bridging the gap between (i) structure and natural language (NL) and (ii) semantically underspecified input and fully specified NL output. Multilingual generation brings in an additional challenge: that of generating into languages with varied word order and morphological properties. In this work, we focus on Abstract Meaning Representations (AMRs) as structured input, where previous research has overwhelmingly focused on generating only into English. We leverage advances in cross-lingual embeddings, pretraining, and multilingual models to create multilingual AMR-to-text models that generate in twenty one different languages. For eighteen languages, based on automatic metrics, our multilingual models surpass baselines that generate into a single language. We analyse the ability of our multilingual models to accurately capture morphology and word order using human evaluation, and find that native speakers judge our generations to be fluent.

show abstract

“…Their supervised model is based on message passing through the topology of the incidence graph of the KG input. Such graph neural networks (Kipf and Welling, 2017;Veličković et al, 2018) have been widely adopted in supervised graph-to-text tasks (Beck et al, 2018;Damonte and Cohen, 2019;Ribeiro et al, 2019Ribeiro et al, , 2020.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing

Schmitt

Sharifzadeh

Tresp

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Knowledge graphs (KGs) can vary greatly from one domain to another. Therefore supervised approaches to both graph-to-text generation and text-to-graph knowledge extraction (semantic parsing) will always suffer from a shortage of domain-specific parallel graphtext data; at the same time, adapting a model trained on a different domain is often impossible due to little or no overlap in entities and relations. This situation calls for an approach that (1) does not need large amounts of annotated data and thus (2) does not need to rely on domain adaptation techniques to work well in different domains. To this end, we present the first approach to unsupervised text generation from KGs and show simultaneously how it can be used for unsupervised semantic parsing. We evaluate our approach on WebNLG v2.1 and a new benchmark leveraging scene graphs from Visual Genome. Our system outperforms strong baselines for both text↔graph conversion tasks without any manual adaptation from one dataset to the other. In additional experiments, we investigate the impact of using different unsupervised objectives. 1

show abstract

Enhancing AMR-to-Text Generation with Dual Graph Representations

Cited by 46 publications

References 32 publications

Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation

Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation

Multilingual AMR-to-Text Generation

An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing

Contact Info

Product

Resources

About