CLAug 22, 2018

Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection

arXiv:1808.07244v21 citations
AI Analysis

This work addresses the challenge of improving matching models for multi-turn conversations in chatbots, offering a domain-specific solution that is incremental over existing methods.

The paper tackles the problem of multi-turn response selection in retrieval-based chatbots by proposing hierarchical contextualized representations, which blend word-level and sentence-level features from pre-training on large-scale conversations. Experimental results show significant and consistent improvements on two benchmark datasets.

In this paper, we study context-response matching with pre-trained contextualized representations for multi-turn response selection in retrieval-based chatbots. Existing models, such as Cove and ELMo, are trained with limited context (often a single sentence or paragraph), and may not work well on multi-turn conversations, due to the hierarchical nature, informal language, and domain-specific words. To address the challenges, we propose pre-training hierarchical contextualized representations, including contextual word-level and sentence-level representations, by learning a dialogue generation model from large-scale conversations with a hierarchical encoder-decoder architecture. Then the two levels of representations are blended into the input and output layer of a matching model respectively. Experimental results on two benchmark conversation datasets indicate that the proposed hierarchical contextualized representations can bring significantly and consistently improvement to existing matching models for response selection.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes