Document retrieval using term term frequency inverse sentence frequency weighting scheme

The need for an efficient method to find the furthermost appropriate document corresponding a particular search query has become crucial due exponential development in number of papers that are now readily available us on web. vector space model (VSM) perfect used “information retrieval”, represents these words as and gives them weights via popular weighting known term frequency inverse (TF-IDF). In this research, work been proposed retrieve most relevant focused representing documents queries vectors comprising average sentence (TF-ISF) instead TF-IDF weight two basic effective similarity measures: Cosine Jaccard were used. Using MS MARCO dataset, article analyzes assesses retrieval effectiveness TF-ISF scheme. result shows with measure retrieves more documents. was evaluated against conventional technique it performs significantly better data (Microsoft-curated Bing queries).