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

By Thiago Castro Ferreira, Iacer Calixto, Sander Wubben, Emiel Krahmer. 2017

36 citations recorded by the source corpus.

In this paper, we study AMR-to-text generation, framing it as a translation task and comparing two different MT approaches (Phrase-based and Neural MT). We systematically study the effects of 3 AMR preprocessing steps (Delexicalisation, Compression, and Linearisation) applied before the MT phase. Our results show that preprocessing indeed helps, although the benefits differ for the two MT models.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Machine Translation, 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 Computer Vision and Pattern Recognition

In Machine Translation

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, neutral): “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”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “Forms such as proper names remain understudied, although recently various researchers have highlighted the problems of proper name generation (Siddharthan et al., 2011; van Deemter, 2016; Ferreira et al., 2017).”
End-to-End Content and Plan Selection for Data-to-Text Generation (2018, methodology): “In order to apply S2S models, a list of attributes in an MR has to be linearized into a sequence of tokens (Konstas et al., 2017; Ferreira et al., 2017).”
Deep Graph Convolutional Encoders for Structured Data to Text Generation (2018, background): “Most previous work casts the graph structured data to text generation task as a sequence-tosequence problem (Gardent et al., 2017b; Ferreira et al., 2017; Konstas et al., 2017).”
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks (2020, methodology): “More works frame graph-to-sequence as a translation task and use either phrase-based (Ferreira et al., 2017; Pour-damghani et al., 2016) or neural-based (Konstas et al., 2017) models.”
Enriching the WebNLG corpus (2018, background): “The paper is organized as follows: Section 2 briefly describes the WebNLG corpus, Section 3 depicts our delexicalization procedure in detail (briefly introduced in Castro Ferreira et al. 2018), Section 4 explains the process of translating the corpus texts to German, Section 5 introduces the interme”
Enhancing AMR-to-Text Generation with Dual Graph Representations (2019, unknown): “In particular, the l -th layer of a GGNN is calculated as: where N ( i ) is the immediate neighborhood of v i , W 1 is a parameter and GRU is a gated recurrent unit (Cho et al., 2014).”