Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis
This addresses sentiment control in chatbots for improving user interaction, but it is incremental as it builds on existing seq2seq methods.
The paper tackled the problem of seq2seq chatbot models ignoring sentiment in responses by proposing five models to scale or adjust sentiment, with reinforcement learning and cycleGAN showing strong performance, and evaluation metrics correlating well with human judgment.
Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. Some research works trying to modify the sentiment of the output sequences were reported. In this paper, we propose five models to scale or adjust the sentiment of the chatbot response: persona-based model, reinforcement learning, plug and play model, sentiment transformation network and cycleGAN, all based on the conventional seq2seq model. We also develop two evaluation metrics to estimate if the responses are reasonable given the input. These metrics together with other two popularly used metrics were used to analyze the performance of the five proposed models on different aspects, and reinforcement learning and cycleGAN were shown to be very attractive. The evaluation metrics were also found to be well correlated with human evaluation.