Linguistic realisation as machine translation: Comparing different
            MT models for AMR-to-text generation

Ferreira, Thiago Castro; Calixto, Iacer; Wubben, Sander; Krahmer, Emiel

doi:10.18653/v1/w17-3501

Cited by 20 publications

(25 citation statements)

References 23 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early works on AMR-to-text generation employ statistical methods (Flanigan et al, 2016b;Pourdamghani et al, 2016;Castro Ferreira et al, 2017) and apply linearization of the graph by means of a depth-first traversal. Recent neural approaches have exhibited success by linearising the input graph and using a sequence-to-sequence architecture.…”

Section: Related Workmentioning

confidence: 99%

Enhancing AMR-to-Text Generation with Dual Graph Representations

Ribeiro¹,

Gardent

Gurevych³

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

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-ofthe-art results on two AMR datasets 1 .

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing AMR-to-Text Generation with Dual Graph Representations

Ribeiro¹,

Gardent

Gurevych³

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…The model has to associate each attribute with its location in a sentence template. However, S2S models can learn wrong associations between inputs and targets with limited data, which was also shown by Ferreira et al (2017). Additionally, consider that we may see the generated texts for similar inputs: There is an expensive British Restaurant called the Eagle.…”

Section: Learning Latent Sentence Templatesmentioning

confidence: 98%

End-to-End Content and Plan Selection for Data-to-Text Generation

Gehrmann¹,

Dai²,

Elder³

et al. 2018

Proceedings of the 11th International Conference on Natural Language Generation

View full text Add to dashboard Cite

Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents a survey of several extensions to sequence-to-sequence models to account for the latent content selection process, particularly variants of copy attention and coverage decoding. We further propose a training method based on diverse ensembling to encourage models to learn distinct sentence templates during training. An empirical evaluation of these techniques shows an increase in the quality of generated text across five automated metrics, as well as human evaluation.

show abstract

“…From an NLP perspective, one of the main research problems in this paradigm has become the choice of the graph encoding strategy. The most popular method is linearizing it into a sequence of tokens and encoding using a variant of a recurrent neural network (RNN) (Gardent et al, 2017;Castro Ferreira et al, 2017;Konstas et al, 2017). Another prominent approach is using graph-to-text neural networks (Song et al, 2018;Trisedya et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Revisiting the Binary Linearization Technique for Surface Realization

Puzikov¹,

Gardent²,

Dagan³

et al. 2019

Proceedings of the 12th International Conference on Natural Language Generation

View full text Add to dashboard Cite

End-to-end neural approaches have achieved state-of-the-art performance in many natural language processing (NLP) tasks. Yet, they often lack transparency of the underlying decision-making process, hindering error analysis and certain model improvements. In this work, we revisit the binary linearization approach to surface realization, which exhibits more interpretable behavior, but was falling short in terms of prediction accuracy. We show how enriching the training data to better capture word order constraints almost doubles the performance of the system. We further demonstrate that encoding both local and global prediction contexts yields another considerable performance boost. With the proposed modifications, the system which ranked low in the latest shared task on multilingual surface realization now achieves best results in five out of ten languages, while being on par with the state-of-the-art approaches in others. 1

show abstract

Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation

Cited by 20 publications

References 23 publications

Enhancing AMR-to-Text Generation with Dual Graph Representations

Enhancing AMR-to-Text Generation with Dual Graph Representations

End-to-End Content and Plan Selection for Data-to-Text Generation

Revisiting the Binary Linearization Technique for Surface Realization

Contact Info

Product

Resources

About