Abstract
Neural network models have achieved impressive results in the field of text classification. However, existing approaches often suffer from insufficient training data in a large-scale text classification involving a large number of categories (e.g., several thousands of categories). Several neural network models have utilized multi-task learning to overcome the limited amount of training data. However, these approaches are also limited to small-scale text classification. In this paper, we propose a novel neural network-based multi-task learning framework for large-scale text classification. To this end, we first treat the different scales of text classification (i.e., large and small numbers of categories) as multiple, related tasks. Then, we train the proposed neural network, which learns small- and large-scale text classification tasks simultaneously. In particular, we further enhance this multi-task learning architecture by using a gate mechanism, which controls the flow of features between the small- and large-scale text classification tasks. Experimental results clearly show that our proposed model improves the performance of the large-scale text classification task with the help of the small-scale text classification task. The proposed scheme exhibits significant improvements of as much as 14% and 5% in terms of micro-averaging and macro-averaging F1-score, respectively, over state-of-the-art techniques.
| Original language | English |
|---|---|
| Title of host publication | The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 853-862 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781450366748 |
| DOIs | |
| Publication status | Published - 2019 May 13 |
| Event | 2019 World Wide Web Conference, WWW 2019 - San Francisco, United States Duration: 2019 May 13 → 2019 May 17 |
Publication series
| Name | The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 |
|---|
Conference
| Conference | 2019 World Wide Web Conference, WWW 2019 |
|---|---|
| Country | United States |
| City | San Francisco |
| Period | 19/5/13 → 19/5/17 |
Fingerprint
Keywords
- Deep Neural Networks
- Large-scale Text Classification
- Multi-task Learning
ASJC Scopus subject areas
- Computer Networks and Communications
- Software
Cite this
From small-scale to large-scale text classification. / Kim, Kang Min; Kim, Yeachan; Lee, Jungho; Lee, Ji Min; Lee, Sang-Geun.
The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 853-862 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - From small-scale to large-scale text classification
AU - Kim, Kang Min
AU - Kim, Yeachan
AU - Lee, Jungho
AU - Lee, Ji Min
AU - Lee, Sang-Geun
PY - 2019/5/13
Y1 - 2019/5/13
N2 - Neural network models have achieved impressive results in the field of text classification. However, existing approaches often suffer from insufficient training data in a large-scale text classification involving a large number of categories (e.g., several thousands of categories). Several neural network models have utilized multi-task learning to overcome the limited amount of training data. However, these approaches are also limited to small-scale text classification. In this paper, we propose a novel neural network-based multi-task learning framework for large-scale text classification. To this end, we first treat the different scales of text classification (i.e., large and small numbers of categories) as multiple, related tasks. Then, we train the proposed neural network, which learns small- and large-scale text classification tasks simultaneously. In particular, we further enhance this multi-task learning architecture by using a gate mechanism, which controls the flow of features between the small- and large-scale text classification tasks. Experimental results clearly show that our proposed model improves the performance of the large-scale text classification task with the help of the small-scale text classification task. The proposed scheme exhibits significant improvements of as much as 14% and 5% in terms of micro-averaging and macro-averaging F1-score, respectively, over state-of-the-art techniques.
AB - Neural network models have achieved impressive results in the field of text classification. However, existing approaches often suffer from insufficient training data in a large-scale text classification involving a large number of categories (e.g., several thousands of categories). Several neural network models have utilized multi-task learning to overcome the limited amount of training data. However, these approaches are also limited to small-scale text classification. In this paper, we propose a novel neural network-based multi-task learning framework for large-scale text classification. To this end, we first treat the different scales of text classification (i.e., large and small numbers of categories) as multiple, related tasks. Then, we train the proposed neural network, which learns small- and large-scale text classification tasks simultaneously. In particular, we further enhance this multi-task learning architecture by using a gate mechanism, which controls the flow of features between the small- and large-scale text classification tasks. Experimental results clearly show that our proposed model improves the performance of the large-scale text classification task with the help of the small-scale text classification task. The proposed scheme exhibits significant improvements of as much as 14% and 5% in terms of micro-averaging and macro-averaging F1-score, respectively, over state-of-the-art techniques.
KW - Deep Neural Networks
KW - Large-scale Text Classification
KW - Multi-task Learning
UR - http://www.scopus.com/inward/record.url?scp=85066910847&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066910847&partnerID=8YFLogxK
U2 - 10.1145/3308558.3313563
DO - 10.1145/3308558.3313563
M3 - Conference contribution
T3 - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
SP - 853
EP - 862
BT - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
PB - Association for Computing Machinery, Inc
ER -