With the recent advancements in information technology there has been a hugesurge in amount of data available. But information retrieval technology has notbeen able to keep up with this pace of information generation resulting in overspending of time for retrieving relevant information. Even though systems existfor assisting users to search a database along with filtering and recommendingrelevant information, but recommendation system which uses content of documentsfor recommendation still have a long way to mature. Here we present a DeepLearning based supervised approach to recommend similar documents based on thesimilarity of content. We combine the C-DSSM model with Word2Vec distributedrepresentations of words to create a novel model to classify a document pair asrelevant/irrelavant by assigning a score to it. Using our model retrieval ofdocuments can be done in O(1) time and the memory complexity is O(n), where nis number of documents.
展开▼