Name
Title | ||
|---|---|---|
Improving Matching Models with Contextualized Word Representations for Multi-turn Response Selection in Retrieval-based Chatbots. |
Abstract | ||
|---|---|---|
We consider matching with pre-trained contextualized word vectors for multi-turn response selection in retrieval-based chatbots. When directly applied to the task, state-of-the-art models, such as CoVe and ELMo, do not work as well as they do on other tasks, due to the hierarchical nature, casual language, and domain-specific word use of conversations. To tackle the challenges, we propose pre-training a sentence-level and a session-level contextualized word vectors by learning a dialogue generation model from large-scale human-human conversations with a hierarchical encoder-decoder architecture. The two levels of vectors are then integrated into the input layer and the output layer of a matching model respectively. Experimental results on two benchmark datasets indicate that the proposed contextualized word vectors can significantly and consistently improve the performance of existing matching models for response selection. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Computation and Language | Architecture,Computer science,Natural language processing,Artificial intelligence,Casual,Machine learning |
DocType | Volume | Citations |
Journal | abs/1808.07244 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chongyang Tao | 1 | 50 | 12.29 |
| Wei Wu | 2 | 262 | 21.59 |
| Can Xu | 3 | 27 | 9.10 |
| Yansong Feng | 4 | 735 | 64.17 |
| Dongyan Zhao | 5 | 998 | 96.35 |
| Rui Yan | 6 | 961 | 76.69 |