Name
Title | ||
|---|---|---|
Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection |
Abstract | ||
|---|---|---|
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.
|
Year | DOI | Venue |
|---|---|---|
2020 | 10.1145/3397271.3401290 | SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval
Virtual Event
China
July, 2020 |
DocType | ISBN | Citations |
Conference | 978-1-4503-8016-4 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chongyang Tao | 1 | 50 | 12.29 |
| Wei Wu | 2 | 262 | 21.59 |
| Yansong Feng | 3 | 735 | 64.17 |
| Dongyan Zhao | 4 | 998 | 96.35 |
| Rui Yan | 5 | 961 | 76.69 |