Designing dialogue systems: A mean, grumpy, sarcastic chatbot in the browser
This work addresses the challenge of designing engaging dialogue systems for users seeking interactive entertainment, but it is incremental as it applies existing deep learning methods to a specific chatbot personality.
The paper tackled the problem of creating a sarcastic and humorous chatbot by training a seq2seq model on 3000 question-answering pairs, resulting in a system that learns patterns quickly and can transfer linguistic structures to new settings, with human raters evaluating its linguistic quality and creativity.
In this work we explore a deep learning-based dialogue system that generates sarcastic and humorous responses from a conversation design perspective. We trained a seq2seq model on a carefully curated dataset of 3000 question-answering pairs, the core of our mean, grumpy, sarcastic chatbot. We show that end-to-end systems learn patterns very quickly from small datasets and thus, are able to transfer simple linguistic structures representing abstract concepts to unseen settings. We also deploy our LSTM-based encoder-decoder model in the browser, where users can directly interact with the chatbot. Human raters evaluated linguistic quality, creativity and human-like traits, revealing the system's strengths, limitations and potential for future research.