Redefining Context Windows for Word Embedding Models: An Experimental Study
This work addresses the understudied role of context windows in distributional semantic models, providing insights for researchers in natural language processing.
The paper systematically analyzes the impact of four hyper-parameters in context windows for word embedding models, finding that cross-sentential contexts improve performance and right-context windows perform surprisingly well in lexical similarity and analogy tasks.
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.