Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
This work addresses the challenge of improving response accuracy in chatbots, which is incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of selecting appropriate responses in multi-turn conversations for retrieval-based chatbots by proposing an interactive matching network (IMN), which achieves state-of-the-art performance on four public datasets.
In this paper, we propose an interactive matching network (IMN) for the multi-turn response selection task. First, IMN constructs word representations from three aspects to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE), which is capable of encoding sentences hierarchically and generating more descriptive representations by aggregating with an attention mechanism, is designed. Finally, the bidirectional interactions between whole multi-turn contexts and response candidates are calculated to derive the matching information between them. Experiments on four public datasets show that IMN outperforms the baseline models on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection.