Pragmatic factors in image description: the case of negations
We provide a qualitative analysis of the descriptions containing negations (no, not, n't, nobody, etc) in the Flickr30K corpus, and a categorization of negation uses. Based on this analysis, we provide a set of requirements that an image description system should have in order to generate negation sentences. As a pilot experiment, we used our categorization to manually annotate sentences containing negations in the Flickr30K corpus, with an agreement score of K=0.67. With this paper, we hope to open up a broader discussion of subjective language in image descriptions.
Code (1)
Tasks
Image DescriptionNegationSimilar Papers 제목 키워드 기반
Pragmatic descriptions of perceptual stimuli
This research proposal discusses pragmatic factors in image description, arguing that current automatic image description systems do not take these factors into account. I present a general model of the human image descr…
Image DescriptionObject RecognitionLearn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations
Existing vision-language models (VLMs) treat text descriptions as a unit, confusing individual concepts in a prompt and impairing visual semantic matching and reasoning. An important aspect of reasoning in logic and lang…
image-classificationImage ClassificationZero-Shot Image ClassificationColors in Context: A Pragmatic Neural Model for Grounded Language Understanding
We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a spe…
Referring ExpressionOn Positivity Bias in Negative Reviews
Prior work has revealed that positive words occur more frequently than negative words in human expressions, which is typically attributed to positivity bias, a tendency for people to report positive views of reality. But…
NegationUnified Pragmatic Models for Generating and Following Instructions
We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain in…
Text Generation