• 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
  • 46
  • 8
  • PDF
Scalar Diversity
TLDR
We present experimental evidence showing that there is considerable variation between the rates at which scalar expressions from different lexical scales give rise to upper-bounded construals. Expand
  • 57
  • 8
  • PDF
Best practices for the human evaluation of automatically generated text
TLDR
This paper provides an overview of how human evaluation is currently conducted, and presents a set of best practices, grounded in the literature. Expand
  • 48
  • 6
  • PDF
Open Dutch WordNet
TLDR
We describe Open Dutch WordNet, which has been derived from the Cornetto database, the Princeton WordNet and open source resources and it has been linked to the Global Wordnet Grid. Expand
  • 34
  • 5
  • PDF
Stereotyping and Bias in the Flickr30K Dataset
TLDR
An untested assumption behind the crowdsourced descriptions of the images in the Flickr30K dataset is that they "focus only on the information that can be obtained from the image alone" (Hodosh et al., 2013, p. 859). Expand
  • 44
  • 2
  • PDF
Sound-based distributional models
TLDR
We present the first results of our efforts to build a perceptually grounded semantic model based on usergenerated and -tagged sounds. Expand
  • 22
  • 1
  • PDF
Measuring the Diversity of Automatic Image Descriptions
TLDR
We consider the production of generic descriptions as a lack of diversity in the output, which we quantify using established metrics and two new metrics that frame image description as a word recall task. Expand
  • 17
  • 1
  • PDF
DIDEC: The Dutch Image Description and Eye-tracking Corpus
TLDR
We present a corpus of spoken Dutch image descriptions, paired with two sets of eye-tracking data: free viewing and description viewing, where we track eye movements while participants produce spoken descriptions of the images they are viewing. Expand
  • 11
  • 1
  • PDF
WordNet-based similarity metrics for adjectives
TLDR
We present new WordNet-based (Fellbaum, 1998) measures to provide reliable estimates of human word similarity ratings. Expand
  • 4
  • 1
  • PDF
Talking about other people: an endless range of possibilities
TLDR
We present a taxonomy of different ways to talk about other people, and show the range of properties that crowd-workers consider in the description process. Expand
  • 4
  • 1
  • PDF
...
1
2
3
4
...