Contextual Skipgram: Training Word Representation Using Context Information
This is an incremental improvement for natural language processing tasks that rely on word embeddings.
The paper tackles the problem of irrelevant words in skip-gram models hindering word representation quality by proposing Contextual Skip-gram, which uses context information to predict words and reduces this impact, resulting in enhanced performance.
The skip-gram (SG) model learns word representation by predicting the words surrounding a center word from unstructured text data. However, not all words in the context window contribute to the meaning of the center word. For example, less relevant words could be in the context window, hindering the SG model from learning a better quality representation. In this paper, we propose an enhanced version of the SG that leverages context information to produce word representation. The proposed model, Contextual Skip-gram, is designed to predict contextual words with both the center words and the context information. This simple idea helps to reduce the impact of irrelevant words on the training process, thus enhancing the final performance