Learning Personas from Dialogue with Attentive Memory Networks
This work addresses the problem of computational narrative analysis and personalized dialogue generation for researchers and developers, but it is incremental as it builds on existing neural methods with attention and memory.
The authors tackled the problem of inferring persona from dialogue by introducing neural models that learn persona embeddings for character trope classification, achieving best performance with a multi-level attention mechanism over utterances and utilizing prior knowledge from textual descriptions.
The ability to infer persona from dialogue can have applications in areas ranging from computational narrative analysis to personalized dialogue generation. We introduce neural models to learn persona embeddings in a supervised character trope classification task. The models encode dialogue snippets from IMDB into representations that can capture the various categories of film characters. The best-performing models use a multi-level attention mechanism over a set of utterances. We also utilize prior knowledge in the form of textual descriptions of the different tropes. We apply the learned embeddings to find similar characters across different movies, and cluster movies according to the distribution of the embeddings. The use of short conversational text as input, and the ability to learn from prior knowledge using memory, suggests these methods could be applied to other domains.