On task effects in NLG corpus elicitation: a replication study using mixed effects modeling

no code implementations • WS 2019 • Emiel van Miltenburg, Merel van de Kerkhof, Ruud Koolen, Martijn Goudbeek, Emiel Krahmer

Task effects in NLG corpus elicitation recently started to receive more attention, but are usually not modeled statistically.

Varying image description tasks: spoken versus written descriptions

1 code implementation • COLING 2018 • Emiel van Miltenburg, Ruud Koolen, Emiel Krahmer

Automatic image description systems are commonly trained and evaluated on written image descriptions.

DIDEC: The Dutch Image Description and Eye-tracking Corpus

no code implementations • COLING 2018 • Emiel van Miltenburg, {\'A}kos K{\'a}d{\'a}r, Ruud Koolen, Emiel Krahmer

We present a corpus of spoken Dutch image descriptions, paired with two sets of eye-tracking data: Free viewing, where participants look at images without any particular purpose, and Description viewing, where we track eye movements while participants produce spoken descriptions of the images they are viewing.

Specificity Task 2

Learning Preferences for Referring Expression Generation: Effects of Domain, Language and Algorithm

no code implementations • WS 2012 • Ruud Koolen, Emiel Krahmer, Mari{\"e}t Theune

Referring Expression Referring expression generation +1