2017
ACL
ACL 2017
AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine
Abstract
AbstractWe propose AliMe Chat, an open-domain chatbot engine that integrates the joint results of Information Retrieval (IR) and Sequence to Sequence (Seq2Seq) based generation models. AliMe Chat uses an attentive Seq2Seq based rerank model to optimize the joint results. Extensive experiments show our engine outperforms both IR and generation based models. We launch AliMe Chat for a real-world industrial application and observe better results than another public chatbot.
🌉
Interdisciplinary Bridge
— Deep Learning and Natural Language Processing
🧭
Keyword Pioneer
— open-domain dialogue
🐣
Hot Topic Early Bird
— dialogue generation
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Minghui Qiu
,
Feng-Lin Li
,
Siyu Wang
,
Xing Gao
,
Yan Chen
,
Weipeng Zhao
,
Haiqing Chen
,
Jun Huang
,
Wei Chu
Topics
Natural Language Processing > Generation > Dialogue Systems
Natural Language Processing > Generation > Text Generation
Natural Language Processing > Applications > Information Retrieval
Natural Language Processing > Applications > Dialogue Systems
Deep Learning > Learning Types > Multi-Modal Learning