Investigation of Sentiment Controllable Chatbot
arXiv:2007.07196
Abstract
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.
arXiv commentarXiv admin note: text overlap with arXiv:1804.02504
References in corpus (11)
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- A Neural Conversational Model
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Style Transfer from Non-Parallel Text by Cross-Alignment
- Deep Reinforcement Learning for Dialogue Generation
- GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
- A Persona-Based Neural Conversation Model
- A Network-based End-to-End Trainable Task-oriented Dialogue System
- Variational Recurrent Auto-Encoders
- Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
- Multiple-Attribute Text Style Transfer