NLPIR SEMINAR Y2019#7
In the new semester, our Lab, Web Search Mining and Security Lab, plans to hold an academic seminar every Monday, and each time a keynote speaker will share understanding of papers on his/her related research with you.
This week’s seminar is organized as follows:
- The seminar time is 1.pm, Mon, at Zhongguancun Technology Park ,Building 5, 1306.
- The lecturer is Ziyu Liu, the paper’s title is SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks.
- The seminar will be hosted by Li Shen.
- Attachment is the paper of this seminar, please download in advance.
Everyone interested in this topic is welcomed to join us. the following is the abstract for this week’s paper.
SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks
Generating texts of different sentiment
labels is getting more and more attention in the area of natural language
generation. Recently, Generative Adversarial Net (GAN) has shown promising
results in text generation. However, the texts generated by GAN usually suffer
from the problems of poor quality, lack of diversity and mode collapse. In this
paper, we propose a novel framework – SentiGAN, which has multiple generators
and one multi-class discriminator, to address the above problems. In our
framework, multiple generators are trained simultaneously, aiming at generating
texts of different sentiment labels without supervision. We propose a penalty
based objective in the generators to force each of them to generate diversified
examples of a specific sentiment label. Moreover, the use of multiple
generators and one multi-class discriminator can make each generator focus on
generating its own examples of a specific sentiment label accurately.
Experimental results on four datasets demonstrate that our model consistently
outperforms several state-of-the-art text generation methods in the sentiment
accuracy and quality of generated texts.