A company has a large set of scientific articles (each of which contains a title, abstract, authors, key words, year of release, main body of the paper and a bibliography). Suggest a means to measure the similarity between two documents based on: Authors listed i) Content of the document ii) iii) iv) Bibliographies Content, authors and bibliographies The company wishes to rank all papers that are relevant to a given query and to then re-order the papers in the answer set according to how authoritative or influential the papers are. Outline an approach that could be used to give a suitable solution for this requirement. Outline a suitable approach to cluster these documents in the collection into useful sub clusters that may be of use in user search tasks. Briefly list and limitations of the approach.