MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation
This addresses a common issue in multi-party conversation modeling for applications like chatbots, though it is incremental as it builds on existing graph neural network methods.
The paper tackles the problem of generating responses in multi-party conversations when addressee labels are partially missing, by proposing MADNet, which uses latent edges and an Expectation-Maximization method to improve graph connectivity and label inference, resulting in outperformance over baselines on Ubuntu IRC benchmarks.
Modeling multi-party conversations (MPCs) with graph neural networks has been proven effective at capturing complicated and graphical information flows. However, existing methods rely heavily on the necessary addressee labels and can only be applied to an ideal setting where each utterance must be tagged with an addressee label. To study the scarcity of addressee labels which is a common issue in MPCs, we propose MADNet that maximizes addressee deduction expectation in heterogeneous graph neural networks for MPC generation. Given an MPC with a few addressee labels missing, existing methods fail to build a consecutively connected conversation graph, but only a few separate conversation fragments instead. To ensure message passing between these conversation fragments, four additional types of latent edges are designed to complete a fully-connected graph. Besides, to optimize the edge-type-dependent message passing for those utterances without addressee labels, an Expectation-Maximization-based method that iteratively generates silver addressee labels (E step), and optimizes the quality of generated responses (M step), is designed. Experimental results on two Ubuntu IRC channel benchmarks show that MADNet outperforms various baseline models on the task of MPC generation, especially under the more common and challenging setting where part of addressee labels are missing.