A Generative Model for category text generation
The neural network model has been the fulcrum of the so-called AI revolution. Although very powerful for pattern-recognition tasks, however, the model has two main drawbacks: it tends to overfit when the training dataset is small, and it is unable to accurately capture category information when the...
Saved in:
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/142638 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-142638 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1426382020-06-26T01:47:33Z A Generative Model for category text generation Li, Yang Pan, Quan Wang, Suhang Yang, Tao Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Category Sentence Generation Generative Adversarial Networks The neural network model has been the fulcrum of the so-called AI revolution. Although very powerful for pattern-recognition tasks, however, the model has two main drawbacks: it tends to overfit when the training dataset is small, and it is unable to accurately capture category information when the class number is large. In this paper, we combine reinforcement learning, generative adversarial networks, and recurrent neural networks to build a new model, termed category sentence generative adversarial network (CS-GAN). Not only the proposed model is able to generate category sentences that enlarge the original dataset, but also it helps improve its generalization capability during supervised training. We evaluate the performance of CS-GAN for the task of sentiment analysis. Quantitative evaluation exhibits the accuracy improvement in polarity detection on a small dataset with high category information. 2020-06-26T01:47:33Z 2020-06-26T01:47:33Z 2018 Journal Article Li, Y., Pan, Q., Wang, S., Yang, T., & Cambria, E. (2018). A Generative Model for category text generation. Information Sciences, 450, 301-315. doi:10.1016/j.ins.2018.03.050 0020-0255 https://hdl.handle.net/10356/142638 10.1016/j.ins.2018.03.050 2-s2.0-85044670076 450 301 315 en Information Sciences © 2018 Elsevier Inc. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Category Sentence Generation Generative Adversarial Networks |
spellingShingle |
Engineering::Computer science and engineering Category Sentence Generation Generative Adversarial Networks Li, Yang Pan, Quan Wang, Suhang Yang, Tao Cambria, Erik A Generative Model for category text generation |
description |
The neural network model has been the fulcrum of the so-called AI revolution. Although very powerful for pattern-recognition tasks, however, the model has two main drawbacks: it tends to overfit when the training dataset is small, and it is unable to accurately capture category information when the class number is large. In this paper, we combine reinforcement learning, generative adversarial networks, and recurrent neural networks to build a new model, termed category sentence generative adversarial network (CS-GAN). Not only the proposed model is able to generate category sentences that enlarge the original dataset, but also it helps improve its generalization capability during supervised training. We evaluate the performance of CS-GAN for the task of sentiment analysis. Quantitative evaluation exhibits the accuracy improvement in polarity detection on a small dataset with high category information. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Li, Yang Pan, Quan Wang, Suhang Yang, Tao Cambria, Erik |
format |
Article |
author |
Li, Yang Pan, Quan Wang, Suhang Yang, Tao Cambria, Erik |
author_sort |
Li, Yang |
title |
A Generative Model for category text generation |
title_short |
A Generative Model for category text generation |
title_full |
A Generative Model for category text generation |
title_fullStr |
A Generative Model for category text generation |
title_full_unstemmed |
A Generative Model for category text generation |
title_sort |
generative model for category text generation |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/142638 |
_version_ |
1681058999743545344 |