Published on Tue Sep 17 2019

Grounding learning of modifier dynamics: An application to color naming

Xudong Han, Philip Schulz, Trevor Cohn

Grounding is crucial for natural language understanding. An important subtask is to understand modified color expressions, such as 'dirty blue' We present a model that learns more complex transformations.

0
0
0
Abstract

Grounding is crucial for natural language understanding. An important subtask is to understand modified color expressions, such as 'dirty blue'. We present a model of color modifiers that, compared with previous additive models in RGB space, learns more complex transformations. In addition, we present a model that operates in the HSV color space. We show that certain adjectives are better modeled in that space. To account for all modifiers, we train a hard ensemble model that selects a color space depending on the modifier color pair. Experimental results show significant and consistent improvements compared to the state-of-the-art baseline model.

Wed Sep 27 2017
NLP
Learning of Colors from Color Names: Distribution and Point Estimation
Color names are often made up of multiple words. Different people have a different idea of what it means to be 'very dark orange'
0
0
0
Mon Jun 13 2016
NLP
Learning to Generate Compositional Color Descriptions
The production of color language is essential for grounded language generation. We present an effective approach to generating color descriptions using recurrent neural networks and a Fourier-transformed color representation.
0
0
0
Fri Oct 09 2020
Artificial Intelligence
Pragmatically Informative Color Generation by Grounding Contextual Modifiers
Grounding language in contextual information is crucial for fine-grained natural language understanding. We propose a computational pragmatics model that formulates the color generation task as a game between speakers and listeners. Our model has an absolute 98% increase in performance for the test cases where the reference colors
0
0
0
Thu Oct 03 2019
NLP
Modeling Color Terminology Across Thousands of Languages
There is an extensive history of scholarship into what constitutes a "basic" color term, as well as a broadly attested acquisition sequence. This paper employs a set of diverse measures on massively cross-linguistic data to operationalize and critique the Berlin and Kay color term hypotheses.
0
0
0
Wed Sep 28 2016
NLP
Character Sequence Models for ColorfulWords
We present a neural network architecture to predict a point in color space from the sequence of characters in the color's name. We evaluate our model on a "color Turing test" and find that, given a name, the colorsPredicted by our model are preferred by annotators.
0
0
0
Tue Apr 17 2018
Computer Vision
Learning to Color from Language
Automatic colorization is the process of adding color to greyscale images. We condition this process on language, allowing end users to manipulate a colorized image by feeding in different captions.
0
0
0