International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 1 - Number 16 |
Year of Publication: 2010 |
Authors: Atul Kumar, Sudip Sanyal |
10.5120/341-519 |
Atul Kumar, Sudip Sanyal . Effect of Pronoun Resolution on Document Similarity. International Journal of Computer Applications. 1, 16 ( February 2010), 60-64. DOI=10.5120/341-519
This paper presents a novel effect of Pronoun Resolution on measurement of document similarity. In this paper we have studied the effect of pronoun resolution within the framework of the Vector Space Model and Probabilistic Latent Semantic Analysis. For this purpose we have developed a Benchmark Corpus consisting of documents whose similarity scores have been given by human beings. We measured the inter-document similarity on these documents using VSM and PLSA. We then performed pronoun resolution on these documents and again calculated the similarity using both methods. Next, the correlation coefficient of the scores was taken with those of the human generated scores. The correlation coefficients clearly demonstrated substantial and consistent improvements of the similarity score after pronoun resolution.