Automatic Suggestions in Conversational Systems
summary
Automatic suggestion features for conversational systems are presented, focusing on techniques to generate and rank reply or action suggestions within chatbots and virtual assistants. The talk discusses implementation details using data-driven approaches and likely covers integration with Python-based tools from the PyData ecosystem for building and evaluating suggestion models.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:53Automatic suggestions problem
- 4:10Classical approaches
- 8:36Neural text generation
- 11:32Retrieval models solution
- 15:52Proposed model details
- 21:38Attention mechanism
- 25:38Candidate ranking
- 27:46Frank AI framework
- 28:28Q&A
related talks
30mConversational AI: Building clever chatbots
33mBuilding the next-generation Conversational AI with Python and Deep Learning
41mConversational Agents at Scale: Retrieval and Generative approaches
38mAI-Powered Conversational Interfaces
50mChatbots state of the art and next challenges
01h 29mGoing Beyond “Sorry, I Didn’t Get That”: Building AI Assistants that Scale...
42mConversational Banking: Transforming Customer Experience with Generative AI
47mTesting Conversational AI