SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.09534 · 2019

Creative GANs for generating poems, lyrics, and metaphors

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1909.09534")
get_code_for_paper("1909.09534")
have("1909.09534")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1909.09534.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1909.09534.svg)](https://syntology.ai/paper/1909.09534)

Connect an agent — have() is free.