2019/09/20 by Ilić, Suzana, Nakano, Reiichiro, Hajnal, Ivo
#Computation and Language (cs.CL) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.1909.09531
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.