Arabic script web page language identifications using decision tree neural networks
In this paper, we propose a hybrid approach of Arabic scripts web page language identification based on decision tree and ARTMAP approaches. We use the decision tree approach to find the general identities of a web document, be it an Arabic script-based or a non-Arabic-based. Then, we use the select...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
Elsevier Limited
2011
|
| Subjects: |
| _version_ | 1796856459186667520 |
|---|---|
| author | Selamat, Ali Ng, Choon Ching |
| author_facet | Selamat, Ali Ng, Choon Ching |
| author_sort | Selamat, Ali |
| collection | ePrints |
| description | In this paper, we propose a hybrid approach of Arabic scripts web page language identification based on decision tree and ARTMAP approaches. We use the decision tree approach to find the general identities of a web document, be it an Arabic script-based or a non-Arabic-based. Then, we use the selected representations of identified pages from the decision tree approach as an input to the ARTMAP neural network for further verification of the diversity of languages detected by the algorithm. From our initial experiments, we found that, although the decision tree approach may achieve a higher accuracy than ARTMAP, the former may not be as reliable as the ARTMAP approach if the language used is extended to other types of Arabic script web documents in different languages (e.g., Urdu, Arabic, Persian, etc.). Therefore, we propose this hybrid decision tree-ARTMAP approach in order to improve the performance of the Arabic script language identification on web documents in a variety of languages. The result shows that the proposed approach has outperformed both decision tree and the default ARTMAP approaches. |
| first_indexed | 2024-03-05T18:43:16Z |
| format | Article |
| id | utm.eprints-28885 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T18:43:16Z |
| publishDate | 2011 |
| publisher | Elsevier Limited |
| record_format | dspace |
| spelling | utm.eprints-288852019-01-31T11:30:15Z http://eprints.utm.my/28885/ Arabic script web page language identifications using decision tree neural networks Selamat, Ali Ng, Choon Ching PL Languages and literatures of Eastern Asia, Africa, Oceania QA75 Electronic computers. Computer science In this paper, we propose a hybrid approach of Arabic scripts web page language identification based on decision tree and ARTMAP approaches. We use the decision tree approach to find the general identities of a web document, be it an Arabic script-based or a non-Arabic-based. Then, we use the selected representations of identified pages from the decision tree approach as an input to the ARTMAP neural network for further verification of the diversity of languages detected by the algorithm. From our initial experiments, we found that, although the decision tree approach may achieve a higher accuracy than ARTMAP, the former may not be as reliable as the ARTMAP approach if the language used is extended to other types of Arabic script web documents in different languages (e.g., Urdu, Arabic, Persian, etc.). Therefore, we propose this hybrid decision tree-ARTMAP approach in order to improve the performance of the Arabic script language identification on web documents in a variety of languages. The result shows that the proposed approach has outperformed both decision tree and the default ARTMAP approaches. Elsevier Limited 2011-01 Article PeerReviewed Selamat, Ali and Ng, Choon Ching (2011) Arabic script web page language identifications using decision tree neural networks. Pattern Recognition, 44 (1). pp. 133-144. ISSN 0031-3203 http://dx.doi.org/10.1016/j.patcog.2010.07.009 DOI:10.1016/j.patcog.2010.07.009 |
| spellingShingle | PL Languages and literatures of Eastern Asia, Africa, Oceania QA75 Electronic computers. Computer science Selamat, Ali Ng, Choon Ching Arabic script web page language identifications using decision tree neural networks |
| title | Arabic script web page language identifications using decision tree neural networks |
| title_full | Arabic script web page language identifications using decision tree neural networks |
| title_fullStr | Arabic script web page language identifications using decision tree neural networks |
| title_full_unstemmed | Arabic script web page language identifications using decision tree neural networks |
| title_short | Arabic script web page language identifications using decision tree neural networks |
| title_sort | arabic script web page language identifications using decision tree neural networks |
| topic | PL Languages and literatures of Eastern Asia, Africa, Oceania QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT selamatali arabicscriptwebpagelanguageidentificationsusingdecisiontreeneuralnetworks AT ngchoonching arabicscriptwebpagelanguageidentificationsusingdecisiontreeneuralnetworks |