Knowledge Amalgam: Generating Jokes and Quotes Together
This work addresses the problem of generating creative text like jokes and quotes for applications in natural language processing, but it appears incremental as it combines existing methods for known tasks.
The paper tackles the challenge of generating humor and quotes separately in computational linguistics by proposing a controlled LSTM architecture trained on both joke and quote datasets with category input, resulting in a single neural net that learns to generate jokes or quotes on demand based on the input category.
Generating humor and quotes are very challenging problems in the field of computational linguistics and are often tackled separately. In this paper, we present a controlled Long Short-Term Memory (LSTM) architecture which is trained with categorical data like jokes and quotes together by passing category as an input along with the sequence of words. The idea is that a single neural net will learn the structure of both jokes and quotes to generate them on demand according to input category. Importantly, we believe the neural net has more knowledge as it's trained on different datasets and hence will enable it to generate more creative jokes or quotes from the mixture of information. May the network generate a funny inspirational joke!