Age of acquisition estimates for 1,208 ambiguous and polysemous words

Unsupervised Learning of Visual Sense Models for Polysemous Words

Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We propose a new method that uses a dictionary to learn models of visual word sense from a large collection of unlabeled web data. The use of LDA to discover a latent sense space makes the model robust despite the very l...

Unsupervised Learning of Visual Sense Models for Polysemous Words

Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We propose a new method that uses a dictionary to learn models of visual word sense from a large collection of unlabeled web data. The use of LDA to discover a latent sense space makes the model robust despite the very l...

Rated age-of-acquisition norms for over 3,200 German words.

Words that have been learned early in life are responded to faster than words that have been acquired later. Subjective ratings of acquisition ages have been successfully employed to study the effect of age of acquisition (AoA). Although a large number of norms exist in many languages, fewer are available for German. Therefore, subjective AoA ratings for 3,259 German words were collected online...

Age - of - acquisition ratings for 30 thousand English words

Discovering Word Senses for Polysemous Words Using Feature Domain Similarity

This paper presents a new clustering algorithm called DSCBC which is designed to automatically discover word senses for polysemous words. DSCBC is an extension of CBC (Pantel and Lin, 2002), and incorporates feature domain similarity: the similarity between the features themselves, obtained a priori from sources external to the dataset. By incorporating the feature domain similarity in clusteri...