Creative GANs for generating poems, lyrics, and metaphors

Abstract

Generative models for text have substantially contributed to tasks like machine translation and language modeling, using maximum likelihood optimization (MLE). However, for creative text generation, where multiple outputs are possible and originality and uniqueness are encouraged, MLE falls short. Methods optimized for MLE lead to outputs that can be generic, repetitive and incoherent. In this work, we use a Generative Adversarial Network framework to alleviate this problem. We evaluate our framework on poetry, lyrics and metaphor datasets, each with widely different characteristics, and report better performance of our objective function over other generative models.

References in corpus (6)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• A Deep Reinforced Model for Abstractive Summarization
• The Curious Case of Neural Text Degeneration
• Regularizing and Optimizing LSTM Language Models
• MaskGAN: Better Text Generation via Filling in the______
• Adversarial Text Generation via Feature-Mover's Distance

Cited by in corpus (4)

• Adversarial Attacks Against Deep Generative Models on Data: A Survey
• A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems
• Youling: an AI-Assisted Lyrics Creation System
• Diptychs of human and machine perceptions