Redefining Context Windows for Word Embedding Models: An Experimental Study

Distributional semantic models learn vector representations of words through the contexts they occur in. Although the choice of context (which often takes the form of a sliding window) has a direct influence on the resulting embeddings, the exact role of this model component is still not fully understood. This paper presents a systematic analysis of context windows based on a set of four distinct hyper-parameters. We train continuous Skip-Gram models on two English-language corpora for various combinations of these hyper-parameters, and evaluate them on both lexical similarity and analogy tasks. Notable experimental results are the positive impact of cross-sentential contexts and the surprisingly good performance of right-context windows.