Learning bi-utterance for multi-turn response selection in retrieval-based chatbots
Multi-turn response selection is essential to retrieval-based chatbots. The task requires multi-turn response selection model to match a response candidate with a conversation context. Existing methods may lose relationship features in the context. In this article, we propose an improved method that...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SAGE Publishing
2019-04-01
|
Series: | International Journal of Advanced Robotic Systems |
Online Access: | https://doi.org/10.1177/1729881419841930 |