008 |
|
140924s2013 ||||||||||||||||| ||eng d |
020 |
|
|a9780494849187
|
035 |
|
|a(MiAaPQ)AAIMR84918
|
040 |
|
|aMiAaPQ|cMiAaPQ
|
100 |
1
|
|aZhao, Ruoxuan.
|
245 |
10
|
|aImproving Retrieval of Information from the Internet.
|
300 |
|
|a167 p.
|
500 |
|
|aSource: Masters Abstracts International, Volume: 51-04.
|
500 |
|
|aAdviser: Joan Morrissey.
|
502 |
|
|aThesis (M.Sc.)--University of Windsor (Canada), 2013.
|
520 |
|
|aTo improve the quality of the search result returned by the internet which makes users have to look through a huge amount of links for the real answers, we utilized the high quality links Google produces and the Information Retrieval technology to implement a Question Answering (QA) system. This system analyzes and downloads the text contents from the relevant web pages Google searches based on the users' questions to build a dynamic knowledge collection; retrieves the relevant passages from the collection and sends the ranked passages back. The users can further refine their questions in the query refinement step for the better answers. A novel search strategy was designed to detect the semantic connections between the question and the documents. This answer retrieval also involves the TF-IDF algorithm and Vector Space Model for the document indexing. We have modified the original Cosine Coefficient Similarity Measurement to rank the candidate answers.
|
590 |
|
|aSchool code: 0115.
|
650 |
4
|
|aComputer Science.
|
650 |
4
|
|aInformation Science.
|
650 |
4
|
|aWeb Studies.
|
690 |
|
|a0984
|
690 |
|
|a0723
|
690 |
|
|a0646
|
710 |
20
|
|aUniversity of Windsor (Canada).|bComputer Science.
|
773 |
0
|
|tMasters Abstracts International|g51-04(E).
|
790 |
|
|a0115
|
791 |
|
|aM.Sc.
|
792 |
|
|a2013
|
793 |
|
|aEnglish
|
095 |
|
|aNLB|bA1 |cN146374|pBOOK|tDDC
|