Investigation of Sentiment Controllable Chatbot
This addresses the need for sentiment-aware chatbots for users seeking emotionally appropriate interactions, but it is incremental as it builds on existing seq2seq methods.
The paper tackled the problem of controlling sentiment in chatbot responses, which conventional seq2seq models ignore, by investigating four models and developing machine-evaluated metrics; reinforcement learning and CycleGAN were found to be very attractive based on human and metric evaluations.
Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. In this paper, we investigate four models to scale or adjust the sentiment of the chatbot response: a persona-based model, reinforcement learning, a plug and play model, and CycleGAN, all based on the seq2seq model. We also develop machine-evaluated metrics to estimate whether the responses are reasonable given the input. These metrics, together with human evaluation, are used to analyze the performance of the four models in terms of different aspects; reinforcement learning and CycleGAN are shown to be very attractive.