Selecting training samples from large and noisy corpora for efficient text classification
59 p.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/47535 |
| _version_ | 1824456295483179008 |
|---|---|
| author | Wong, Daji |
| author2 | Manoranjan Dash |
| author_facet | Manoranjan Dash Wong, Daji |
| author_sort | Wong, Daji |
| collection | NTU |
| description | 59 p. |
| first_indexed | 2025-02-19T03:51:50Z |
| format | Thesis |
| id | ntu-10356/47535 |
| institution | Nanyang Technological University |
| last_indexed | 2025-02-19T03:51:50Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/475352019-12-10T13:02:26Z Selecting training samples from large and noisy corpora for efficient text classification Wong, Daji Manoranjan Dash Wee Kim Wee School of Communication and Information DRNTU::Engineering::Computer science and engineering::Computing methodologies::Document and text processing 59 p. In this thesis, an algorithm is presented that selects samples of documents for training text classifiers. Often the number of documents is very large and the documents are noisy. Both for efficiency purposes and accuracy purposes, one need good samples not just blind samples such as that of simple random sampling. The proposed algorithm is far superior to simple random sampling both for small sampling ratios and in the presence of noise. The proposed algorithm is based on a simple fact that the terms in the set of training sample documents should have approximately equal document frequency as in the whole set (not including the test set). Master of Science (Information Studies) 2011-12-27T08:36:21Z 2011-12-27T08:36:21Z 2009 2009 Thesis http://hdl.handle.net/10356/47535 Nanyang Technological University application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Document and text processing Wong, Daji Selecting training samples from large and noisy corpora for efficient text classification |
| title | Selecting training samples from large and noisy corpora for efficient text classification |
| title_full | Selecting training samples from large and noisy corpora for efficient text classification |
| title_fullStr | Selecting training samples from large and noisy corpora for efficient text classification |
| title_full_unstemmed | Selecting training samples from large and noisy corpora for efficient text classification |
| title_short | Selecting training samples from large and noisy corpora for efficient text classification |
| title_sort | selecting training samples from large and noisy corpora for efficient text classification |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Document and text processing |
| url | http://hdl.handle.net/10356/47535 |
| work_keys_str_mv | AT wongdaji selectingtrainingsamplesfromlargeandnoisycorporaforefficienttextclassification |