LSTM based Conversation Models
This work addresses conversational AI for chatbots or dialogue systems, but it is incremental as it builds on existing LSTM methods with role and context integration.
The paper tackled the problem of modeling two-party conversations by incorporating context and participant roles into LSTM language models, resulting in improved performance over traditional LSTMs with better perplexity and response ranking on the Ubuntu Dialog Corpus.
In this paper, we present a conversational model that incorporates both context and participant role for two-party conversations. Different architectures are explored for integrating participant role and context information into a Long Short-term Memory (LSTM) language model. The conversational model can function as a language model or a language generation model. Experiments on the Ubuntu Dialog Corpus show that our model can capture multiple turn interaction between participants. The proposed method outperforms a traditional LSTM model as measured by language model perplexity and response ranking. Generated responses show characteristic differences between the two participant roles.