Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

TL;DR

This paper introduces U2U-IMN, a novel model for multi-turn response selection in chatbots that considers utterance-to-utterance interactions, leading to improved performance across multiple datasets.

Contribution

The paper presents a new utterance-to-utterance interactive matching network that enhances multi-turn response selection by modeling detailed interactions between all utterances.

Findings

Achieved state-of-the-art results on four public datasets.

Outperformed baseline methods on all evaluation metrics.

Demonstrated cross-domain applicability of the proposed model.

Abstract

This paper proposes an utterance-to-utterance interactive matching network (U2U-IMN) for multi-turn response selection in retrieval-based chatbots. Different from previous methods following context-to-response matching or utterance-to-response matching frameworks, this model treats both contexts and responses as sequences of utterances when calculating the matching degrees between them. For a context-response pair, the U2U-IMN model first encodes each utterance separately using recurrent and self-attention layers. Then, a global and bidirectional interaction between the context and the response is conducted using the attention mechanism to collect the matching information between them. The distances between context and response utterances are employed as a prior component when calculating the attention weights. Finally, sentence-level aggregation and context-response-level aggregation are executed in turn to obtain the feature vector for matching degree prediction. Experiments on four public datasets showed that our proposed method outperformed baseline methods on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection.