Towards a Sentiment-Aware Conversational Agent
This work addresses the need for more emotionally intelligent conversational agents, though it is incremental as it builds on existing text generation methods with sentiment guidance.
The authors tackled the problem of generating sentiment-appropriate replies in conversational agents by proposing an end-to-end model that predicts sentiment and conditions text generation on it, resulting in clear improvements in both sentiment expression and text quality as shown by automatic and human evaluations.
In this paper, we propose an end-to-end sentiment-aware conversational agent based on two models: a reply sentiment prediction model, which leverages the context of the dialogue to predict an appropriate sentiment for the agent to express in its reply; and a text generation model, which is conditioned on the predicted sentiment and the context of the dialogue, to produce a reply that is both context and sentiment appropriate. Additionally, we propose to use a sentiment classification model to evaluate the sentiment expressed by the agent during the development of the model. This allows us to evaluate the agent in an automatic way. Both automatic and human evaluation results show that explicitly guiding the text generation model with a pre-defined set of sentences leads to clear improvements, both regarding the expressed sentiment and the quality of the generated text.