• Publications
  • Influence
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
TLDR
We present a systematic comparison between neural pipeline and end-to-end data- to-text approaches for the generation of output text from RDF triples. Expand
  • 26
  • 6
  • PDF
Towards more variation in text generation: Developing and evaluating variation models for choice of referential form
TLDR
We describe two models that account for individual variation in the choice of referential form in automatically generated text: a Naive Bayes model and a Recurrent Neural Network. Expand
  • 18
  • 5
  • PDF
Enriching the WebNLG corpus
TLDR
This paper describes the enrichment of WebNLG corpus (Gardent et al., 2017a,b), with the aim to further extend its usefulness as a resource for evaluating common NLG tasks, including Discourse Ordering, Lexicalization and Referring Expression Generation. Expand
  • 15
  • 4
  • PDF
Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation
TLDR
We systematically study the effects of 3 AMR preprocessing steps (Delexicalisation, Compression, and Linearisation) applied before the MT phase. Expand
  • 23
  • 4
  • PDF
NeuralREG: An end-to-end approach to referring expression generation
TLDR
In this paper, we present a new approach (NeuralREG), relying on deep neural networks, which makes decisions about form and content of references to discourse entities in text in one go without explicit feature extraction. Expand
  • 18
  • 3
  • PDF
Generating flexible proper name references in text: Data, models and evaluation
TLDR
This study introduces a statistical model able to generate variations of a proper name, taking into account the person to be mentioned, the discourse context and individual variation. Expand
  • 9
  • 2
  • PDF
Surface Realization Shared Task 2018 (SR18): The Tilburg University Approach
TLDR
This study describes the approach developed by the Tilburg University team to the shallow track of the Multilingual Surface Realization Shared Task 2019 (SR’19) (Mille et al., 2019). Expand
  • 9
  • 1
  • PDF
RDF2PT: Generating Brazilian Portuguese Texts from RDF Data
TLDR
We propose RDF2PT, a rule-based approach that verbalizes RDF data to Brazilian Portuguese language. Expand
  • 9
  • 1
  • PDF
Improving the generation of personalised descriptions
TLDR
We propose a simple training method for speakerdependent REG in which speakers are grouped into profiles according to the speaker’s referential behaviour. Expand
  • 3
  • 1
  • PDF
Referring Expression Generation: Taking Speakers' Preferences into Account
TLDR
We describe a classification-based approach to referring expression generation (REG) making use of standard context-related features, and an extension that adds speaker- related features. Expand
  • 20
  • PDF