AMR-to-text Generation with Synchronous Node Replacement Grammar

By Linfeng Song, Xiaochang Peng, Zhiguo Wang, Daniel Gildea. 2017

55 citations recorded by the source corpus.

This paper addresses the task of AMR-to-text generation by leveraging synchronous node replacement grammar. During training, graph-to-string rules are learned using a heuristic extraction algorithm. At test time, a graph transducer is applied to collapse input AMRs and generate output sentences. Evaluated on a standard benchmark, our method gives the state-of-the-art result.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, 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

1. Mohit Bansal
2. Caiming Xiong
3. Richard Socher
4. Iryna Gurevych
5. Luke S. Zettlemoyer
6. Percy Liang
7. Dragomir R. Radev
8. Graham Neubig

In Information Systems

1. Tao Yu
2. Xi Victoria Lin
3. Dragomir R. Radev
4. Caiming Xiong
5. Rui Zhang
6. Richard Socher
7. Gholamreza Haffari
8. Leonardo F. R. Ribeiro

In Natural Language Processing

1. Caiming Xiong
2. Mohit Bansal
3. Richard Socher
4. Iryna Gurevych
5. Mirella Lapata
6. Dragomir R. Radev
7. Percy Liang
8. Luke S. Zettlemoyer

In Natural Language Generation

1. Leonardo F. R. Ribeiro
2. Emiel Krahmer
3. Iryna Gurevych
4. Thiago Castro Ferreira
5. Rui Zhang
6. Claire Gardent
7. Richard Socher
8. Caiming Xiong

Citations in the corpus

• DART: Open-Domain Structured Data Record to Text Generation (2020, background): “Data-to-text datasets take different formats, including slot-value pairs, Abstract Meaning Representation (AMR) (Flanigan et al., 2016; Ferreira et al., 2017; Song et al., 2017; Zhu et al., 2019a; Ribeiro et al., 2019; Damonte and Cohen, 2019; Wang et al., 2020a; Zhao et al., 2020b; Shen et al., 202”
• Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks (2020, methodology): “2017) use heuristic extraction algorithm to learn graph-to-string rules.”
• Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation (2017, methodology): “The ones of Song et al. (2016) and Song et al. (2017) were trained with 16,833 pairs from the LDC2015E86 corpus.”
• Graph-to-Sequence Learning using Gated Graph Neural Networks (2018, background): “Applications Early work on AMR generation employs grammars and transducers (Flanigan et al., 2016; Song et al., 2017).”
• Modeling Graph Structure in Transformer for Better AMR-to-Text Generation (2019, unknown): “Song et al. (2017) use synchronous node replacement grammar (SNRG) to generate text.”
• Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs (2020, methodology): “In a similar direction, AMR-to-text generation models employ LSTMs (Song et al., 2017) and dense connections (Guo et al.”