Inproceedings3837: Unterschied zwischen den Versionen
Xi5455 (Diskussion | Beiträge) K |
Xi5455 (Diskussion | Beiträge) K |
||
Zeile 29: | Zeile 29: | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=It is beyond human capabilities to analyze a huge amount of short text produced on the World Wide Web in the form of search queries, social media platforms, etc. Due to many difficulties underlying short text for automated processing, i.e, sparsity and insufficient context, the traditional text classification approaches cannot easily be applied to short text. This study discusses a Convolutional Neural Network (CNN) based approach for short text classification. Given a short text, the model generates the text representation by leveraging words together with the entities. To validate the effectiveness of the model, several experiments have been conducted on different datasets. The results suggest that the proposed model is capable of performing short text classification with a high accuracy and outperforms the baseline. | |Abstract=It is beyond human capabilities to analyze a huge amount of short text produced on the World Wide Web in the form of search queries, social media platforms, etc. Due to many difficulties underlying short text for automated processing, i.e, sparsity and insufficient context, the traditional text classification approaches cannot easily be applied to short text. This study discusses a Convolutional Neural Network (CNN) based approach for short text classification. Given a short text, the model generates the text representation by leveraging words together with the entities. To validate the effectiveness of the model, several experiments have been conducted on different datasets. The results suggest that the proposed model is capable of performing short text classification with a high accuracy and outperforms the baseline. | ||
+ | |Download=2020-Alam-Bie-Türker-Sack-EKAW-Short-Text-Classification.pdf | ||
|DOI Name=10.1007/978-3-030-61244-3_9 | |DOI Name=10.1007/978-3-030-61244-3_9 | ||
|Forschungsgruppe=Information Service Engineering | |Forschungsgruppe=Information Service Engineering | ||
}} | }} |
Aktuelle Version vom 17. November 2022, 10:33 Uhr
Entity-based Short Text Classification using Convolutional Neural Networks
Entity-based Short Text Classification using Convolutional Neural Networks
Published: 2020
September
Herausgeber: Springer
Buchtitel: Proceedings of Knowledge Engineering and Knowledge Management
Seiten: 136-146
Verlag: Springer
Erscheinungsort: Cham
Organisation: 22nd International Conference, EKAW 2020
Referierte Veröffentlichung
BibTeX
Kurzfassung
It is beyond human capabilities to analyze a huge amount of short text produced on the World Wide Web in the form of search queries, social media platforms, etc. Due to many difficulties underlying short text for automated processing, i.e, sparsity and insufficient context, the traditional text classification approaches cannot easily be applied to short text. This study discusses a Convolutional Neural Network (CNN) based approach for short text classification. Given a short text, the model generates the text representation by leveraging words together with the entities. To validate the effectiveness of the model, several experiments have been conducted on different datasets. The results suggest that the proposed model is capable of performing short text classification with a high accuracy and outperforms the baseline.
Download: Media:2020-Alam-Bie-Türker-Sack-EKAW-Short-Text-Classification.pdf
DOI Link: 10.1007/978-3-030-61244-3_9
Information Service Engineering