Generation from Abstract Meaning Representation using Tree Transducers

By Jeffrey Flanigan, Chris Dyer, Noah A. Smith, Jaime G. Carbonell. 2016

110 citations recorded by the source corpus.

Language generation from purely semantic representations is a challenging task. This paper addresses generating English from the Ab-stract Meaning Representation (AMR), consisting of re-entrant graphs whose nodes are concepts and edges are relations. The new method is trained statistically from AMR-annotated English and consists of two major steps: (i) generating an appropriate spanning tree for the AMR, and (ii) applying tree-to-string transducers to generate English. The method relies on discriminative learning and an argument realization model to overcome data sparsity. Initial tests on held-out data show good promise despite the complexity of the task. The system is available open-source as part of JAMR at:

Subfields: Artificial Intelligence, Natural Language Generation, Computational Linguistics & Semantics

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

In Computational Linguistics & Semantics

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”
GPT-too: A Language-Model-First Approach for AMR-to-Text Generation (2020, methodology): “We tokenize each input text using The JAMR toolkit (Flanigan et al., 2014).”
Triple-to-Text: Converting RDF Triples into High-Quality Natural Languages via Optimizing an Inverse KL Divergence (2019, methodology): “lexicalization [14]. Kukich [33] designed a knowledge-based report generator which infers semantic messages from the data and then maps that information into a grammar-based template. Flanigan et al. [22] proposed a two-stage method for natural language generation from Abstract Meaning Representatio”
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation (2017, methodology): “Flanigan et al. (2016b) specify a number of tree-to-string transduction rules based on alignments and POS-based features that are used to drive a tree-based SMT system.”
AMR-To-Text Generation with Graph Transformer (2020, methodology): “9 Tree2Str (Flanigan et al., 2016) 23.”
PaperRobot: Incremental Draft Generation of Scientific Ideas (2019, methodology): “…Networks have been applied to generate nat-ural language to describe structured knowledge bases (Duma and Klein, 2013; Konstas and Lap-ata, 2013; Flanigan et al., 2016; Hardy and Vla-chos, 2018; Pourdamghani et al., 2016; Trisedya et al., 2018; Xu et al., 2018; Madotto et al., 2018; Nie et al.,…”
Modeling Graph Structure in Transformer for Better AMR-to-Text Generation (2019, methodology): “Flanigan et al. (2016) ﬁrst transform an AMR graph into a tree, then specify a number of tree-to-string transduction rules based on alignments that are used to drive a tree-based SMT model (Graehl and Knight, 2004).”
Enhancing AMR-to-Text Generation with Dual Graph Representations (2019, unknown): “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.”
A Human Evaluation of AMR-to-English Generation Systems (2020, background): “They ﬁnd that their rule-based sys-tem is on par with ISI and much better than JAMR, despite having a much lower BLEU.”
Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation (2017, methodology): “This method yields better results than Flanigan et al. (2016) on development and test set from the LDC2014T12 corpus.”
AMR-to-text Generation with Synchronous Node Replacement Grammar (2017, background): “, 2016), there has been little work on AMR-to-text generation (Flanigan et al., 2016; Song et al., 2016; Pourdamghani et al., 2016).”
Describing a Knowledge Base (2018, background): “18 induce templates and then fill appropriate content into slots (Kukich, 1983; Cawsey et al., 1997; Angeli et al., 2010; Duma and Klein, 2013; Konstas and Lapata, 2013a; Flanigan et al., 2016a).”
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs (2020, unknown): “Early efforts for graph-to-text generation employ statistical methods (Flanigan et al., 2016; Pour-damghani et al., 2016; Song et al., 2017).”
Graph-to-Sequence Learning using Gated Graph Neural Networks (2018, methodology): “Applications Early work on AMR generation employs grammars and transducers (Flanigan et al., 2016; Song et al., 2017).”