Papers by Emiel van Miltenburg
Measuring the Diversity of Automatic Image Descriptions (C18-1)
Copied to clipboard
| Challenge: | a lack of diversity in automatic image description systems is a general problem in natural language generation . authors use established metrics to evaluate system performance on the head of the vocabulary . automatic image descriptions are difficult because of the unbounded range of variation in natural languages . |
| Approach: | They propose to frame automatic image description as a word recall task to quantify the production of generic sentences as 'undiversity' they propose to use established metrics to evaluate the diversity of the output . |
| Outcome: | The proposed metrics evaluate the diversity of sentences generated by state-of-the-art systems on a MS COCO dataset. |
DIDEC: The Dutch Image Description and Eye-tracking Corpus (C18-1)
Copied to clipboard
| Challenge: | Using a corpus of spoken Dutch image descriptions and eye-tracking data, we can gain a deeper understanding of the image description task, especially how visual attention is correlated with the image descriptions. |
| Approach: | They present a corpus of spoken Dutch image descriptions paired with eye-tracking data from Free viewing and Description viewing tasks to provide an initial analysis of self-corrections in image descriptions. |
| Outcome: | The results show that the eye-tracking data for the description viewing task is more coherent than for the free-viewing task, and that variation in image descriptions is only moderately correlated across different languages. |
Preregistering NLP research (2021.naacl-main)
Copied to clipboard
| Challenge: | Preregistration refers to specifying what you are going to do, and what you expect to find in your study, before carrying out the study. |
| Approach: | They propose to use preregistration to specify what you are going to do and what you expect to find in your study, and propose several preregistrations questions for different kinds of studies. |
| Outcome: | The proposed preregistration form could provide firmer grounds for slow science in NLP research. |
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures (D19-1)
Copied to clipboard
| Challenge: | Traditionally, data-to-text applications have been designed using a modular pipeline architecture, in which the non-linguistic input data is converted into natural language through several intermediate transformations. |
| Approach: | They propose to use Gated-Recurrent Units and Transformer to implement neural pipelines for data-to-text generation. |
| Outcome: | The proposed models generalize better to unseen inputs and have better performance than the existing pipeline architectures. |