Survey of the state of the art in natural language generation: Core tasks, applications and evaluation
This paper surveys the current state of the art in Natural Language Generation (NLG),
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …
Decoding methods in neural language generation: a survey
Neural encoder-decoder models for language generation can be trained to predict words
directly from linguistic or non-linguistic inputs. When generating with these so-called end-to …
directly from linguistic or non-linguistic inputs. When generating with these so-called end-to …
The WebNLG challenge: Generating text from RDF data
C Gardent, A Shimorina, S Narayan… - 10th International …, 2017 - research.ed.ac.uk
The WebNLG challenge consists in mapping sets of RDF triples to text. It provides a
common benchmark on which to train, evaluate and compare “microplanners”, ie generation …
common benchmark on which to train, evaluate and compare “microplanners”, ie generation …
The gem benchmark: Natural language generation, its evaluation and metrics
We introduce GEM, a living benchmark for natural language Generation (NLG), its
Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving …
Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving …
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
Traditionally, most data-to-text applications have been designed using a modular pipeline
architecture, in which non-linguistic input data is converted into natural language through …
architecture, in which non-linguistic input data is converted into natural language through …
Deep graph convolutional encoders for structured data to text generation
D Marcheggiani, L Perez-Beltrachini - arXiv preprint arXiv:1810.09995, 2018 - arxiv.org
Most previous work on neural text generation from graph-structured data relies on standard
sequence-to-sequence methods. These approaches linearise the input graph to be fed to a …
sequence-to-sequence methods. These approaches linearise the input graph to be fed to a …
Enhancing AMR-to-text generation with dual graph representations
LFR Ribeiro, C Gardent, I Gurevych - arXiv preprint arXiv:1909.00352, 2019 - arxiv.org
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 …
a challenging task due to the inherent difficulty in how to properly encode the structure of a …
[PDF][PDF] Generation from abstract meaning representation using tree transducers
Abstract Language generation from purely semantic representations is a challenging task.
This paper addresses generating English from the Abstract Meaning Representation (AMR) …
This paper addresses generating English from the Abstract Meaning Representation (AMR) …
Scigen: a dataset for reasoning-aware text generation from scientific tables
We introduce SciGen, a new challenge dataset consisting of tables from scientific articles
and their corresponding descriptions, for the task of reasoning-aware data-to-text …
and their corresponding descriptions, for the task of reasoning-aware data-to-text …
Revisiting challenges in data-to-text generation with fact grounding
H Wang - arXiv preprint arXiv:2001.03830, 2020 - arxiv.org
Data-to-text generation models face challenges in ensuring data fidelity by referring to the
correct input source. To inspire studies in this area, Wiseman et al.(2017) introduced the …
correct input source. To inspire studies in this area, Wiseman et al.(2017) introduced the …