Jacob Turton


2020

pdf bib
Extrapolating Binder Style Word Embeddings to New Words
Jacob Turton | David Vinson | Robert Smith
Proceedings of the Second Workshop on Linguistic and Neurocognitive Resources

Word embeddings such as Word2Vec not only uniquely identify words but also encode important semantic information about them. However, as single entities they are difficult to interpret and their individual dimensions do not have obvious meanings. A more intuitive and interpretable feature space based on neural representations of words was presented by Binder and colleagues (2016) but is only available for a very limited vocabulary. Previous research (Utsumi, 2018) indicates that Binder features can be predicted for words from their embedding vectors (such as Word2Vec), but only looked at the original Binder vocabulary. This paper aimed to demonstrate that Binder features can effectively be predicted for a large number of new words and that the predicted values are sensible. The results supported this, showing that correlations between predicted feature values were consistent with those in the original Binder dataset. Additionally, vectors of predicted values performed comparatively to established embedding models in tests of word-pair semantic similarity. Being able to predict Binder feature space vectors for any number of new words opens up many uses not possible with the original vocabulary size.