CLJun 22, 2020

Efficient text generation of user-defined topic using generative adversarial networks

arXiv:2006.12005v1996 citations
AI Analysis

This addresses a practical bottleneck for users needing customizable text generation, though it is incremental as it builds on existing GAN frameworks.

The study tackled the inefficiency of retraining entire GANs for user-defined topics and sentiments by proposing a two-level discriminator system (UD-GAN), which reduced generation time compared to other GAN-based methods while maintaining relevance to user inputs.

This study focused on efficient text generation using generative adversarial networks (GAN). Assuming that the goal is to generate a paragraph of a user-defined topic and sentimental tendency, conventionally the whole network has to be re-trained to obtain new results each time when a user changes the topic. This would be time-consuming and impractical. Therefore, we propose a User-Defined GAN (UD-GAN) with two-level discriminators to solve this problem. The first discriminator aims to guide the generator to learn paragraph-level information and sentence syntactic structure, which is constructed by multiple-LSTMs. The second one copes with higher-level information, such as the user-defined sentiment and topic for text generation. The cosine similarity based on TF-IDF and length penalty are adopted to determine the relevance of the topic. Then, the second discriminator is re-trained with the generator if the topic or sentiment for text generation is modified. The system evaluations are conducted to compare the performance of the proposed method with other GAN-based ones. The objective results showed that the proposed method is capable of generating texts with less time than others and the generated text is related to the user-defined topic and sentiment. We will further investigate the possibility of incorporating more detailed paragraph information such as semantics into text generation to enhance the result.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes