Learning of Colors from Color Names: Distribution and Point Estimation
This work addresses a natural language understanding task for color estimation, but it is incremental as it compares existing methods without introducing new techniques.
The paper tackled the problem of estimating colors from multi-word color names using neural networks, finding that the simple sum of word embeddings method generally outperformed more complex models like RNNs and CNNs across evaluations.
Color names are often made up of multiple words. As a task in natural language understanding we investigate in depth the capacity of neural networks based on sums of word embeddings (SOWE), recurrence (LSTM and GRU based RNNs) and convolution (CNN), to estimate colors from sequences of terms. We consider both point and distribution estimates of color. We argue that the latter has a particular value as there is no clear agreement between people as to what a particular color describes -- different people have a different idea of what it means to be ``very dark orange'', for example. Surprisingly, despite it's simplicity, the sum of word embeddings generally performs the best on almost all evaluations.