This solution uses an unsupervised learning method that solves problem of Bias in unstructured data (Text Corpus). It identifies and reduces the bias present in the word embeddings. The user can target a specific bias (Gender, Age, Race etc.) to be identified and mitigated, without loss in semantic meaning of words in the corpus. These trained and de-biased word vectors can then be utilized in language models powering applications like unbiased word prediction, unbiased word suggestion for replacement words in sentences, unbiased sentence generation, etc.