A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation
This work addresses the issue of poor conversational quality in AI systems, but it appears incremental as it builds on existing methods with specific modifications.
The paper tackled the problem of neural language models generating generic, illogical, and emotionless replies by proposing a syntactically constrained bidirectional-asynchronous approach for emotional conversation generation, which improved diversity, logic, and emotion compared to baselines.
Traditional neural language models tend to generate generic replies with poor logic and no emotion. In this paper, a syntactically constrained bidirectional-asynchronous approach for emotional conversation generation (E-SCBA) is proposed to address this issue. In our model, pre-generated emotion keywords and topic keywords are asynchronously introduced into the process of decoding. It is much different from most existing methods which generate replies from the first word to the last. Through experiments, the results indicate that our approach not only improves the diversity of replies, but gains a boost on both logic and emotion compared with baselines.