Published on Sun Oct 27 2019

Memeify: A Large-Scale Meme Generation System

Suryatej Reddy Vyalla, Vishaal Udandarao, Tanmoy Chakraborty

Meme datasets available online are either specific to a context or contain no class information. Here, we prepare a large-scale dataset of memes with captions and class labels. The dataset consists of 1.1 million meme captions from 128 classes.

0
0
0
Abstract

Interest in the research areas related to meme propagation and generation has been increasing rapidly in the last couple of years. Meme datasets available online are either specific to a context or contain no class information. Here, we prepare a large-scale dataset of memes with captions and class labels. The dataset consists of 1.1 million meme captions from 128 classes. We also provide reasoning for the existence of broad categories, called "themes" across the meme dataset; each theme consists of multiple meme classes. Our generation system uses a trained state-of-the-art transformer-based model for caption generation by employing an encoder-decoder architecture. We develop a web interface, called Memeify for users to generate memes of their choice, and explain in detail, the working of individual components of the system. We also perform a qualitative evaluation of the generated memes by conducting a user study. A link to the demonstration of the Memeify system is https://youtu.be/P_Tfs0X-czs.

Fri Jun 08 2018
Machine Learning
Dank Learning: Generating Memes Using Deep Neural Networks
System can be conditioned on not only an image but also a user-defined label relating to the meme template. The system uses apretrained Inception-v3 network to return an image embedding.
0
0
0
Thu Mar 24 2016
NLP
Neural Text Generation from Structured Data with Application to the Biography Domain
This paper introduces a neural model for concept-to-text generation that scales to large, rich domains. The dataset is vastly more diverse with a 400k vocabulary, compared to a few hundred words for Weathergov or Robocup.
0
0
0
Thu Apr 30 2020
NLP
memeBot: Towards Automatic Image Meme Generation
Image memes have become a widespread tool used by people for interacting and exchanging ideas over social media, blogs, and open messengers. This work proposes to treat automatic image meme generation as a translation process. An encoder is used to map the selected meme template and the input sentence into a meme
0
0
0
Fri Nov 06 2020
NLP
The ApposCorpus: A new multilingual, multi-domain dataset for factual appositive generation
News articles, image captions, product reviews and many other texts mention people and organizations whose name recognition could vary for different audiences. In such cases, background information about the named entities could provide in the form of an appositive noun phrase.
0
0
0
Tue Sep 04 2018
Artificial Intelligence
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
Texar is an open-source toolkit aiming to support a broad set of text generation tasks. The toolkit extracts common patterns underlying the diverse tasks and methodologies. Texar supports both TensorFlow and PyTorch.
0
0
0
Wed Jun 28 2017
NLP
The E2E Dataset: New Challenges For End-to-End Generation
This paper describes the E2E data, a new dataset for training end-to-end, data-driven natural language generation systems. The dataset is ten times bigger than existing, frequently used datasets in this area. The human reference texts show more lexical richness and syntactic variation.
0
0
0