Cross-language text classification with convolutional neural networks from scratch
dc.contributor.author | Enweiji, Musbah | |
dc.contributor.author | Lehinevych, Taras | |
dc.contributor.author | Glybovets, Andrii | |
dc.date.accessioned | 2018-07-02T11:45:01Z | |
dc.date.available | 2018-07-02T11:45:01Z | |
dc.date.issued | 2017 | |
dc.description.abstract | Cross language classification is an important task in multilingual learning, where documents in different languages often share the same set of categories. The main goal is to reduce the labeling cost of training classification model for each individual language. The novel approach by using Convolutional Neural Networks for multilingual language classification is proposed in this article. It learns representation of knowledge gained from languages. Moreover, current method works for new individual language, which was not used in training. The results of empirical study on large dataset of 21 languages demonstrate robustness and competitiveness of the presented approach. | en_US |
dc.identifier.citation | Enweiji M. Z. Cross-language text classification with convolutional neural networks from scratch / Musbah Zaid Enweiji, Taras Lehinevych, Аndrey Glybovets // EUREKA: Physics and Engineering. - 2017. - № 2. - С. 24-33. | en_US |
dc.identifier.issn | 2461-4254 | |
dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/13465 | |
dc.identifier.uri | http://dx.doi.org/10.21303/2461-4262.2017.00304 | |
dc.language.iso | en | en_US |
dc.relation.source | EUREKA: Physics and Engineering. - 2017. - № 2 | en_US |
dc.status | first published | en_US |
dc.subject | text classification | en_US |
dc.subject | convolutional neural network | en_US |
dc.subject | cross-language text classification | en_US |
dc.subject | multilingual classification | en_US |
dc.subject | transfer learning | en_US |
dc.subject | inductive transfer | en_US |
dc.subject | supervised learning | en_US |
dc.subject | artificial neural network | en_US |
dc.subject | article | en_US |
dc.title | Cross-language text classification with convolutional neural networks from scratch | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Cross_language_text_classification_with_convolutional_neural_networks.pdf
- Size:
- 909.29 KB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 7.54 KB
- Format:
- Item-specific license agreed upon to submission
- Description: