Conversational AI
Better collaboration via conversations - human-human and human-machines
Conversations happen everywhere!
Communication platforms such as Slack have changed the ways we work and share. Salesforce AI Research focuses on building cutting edge AI solutions to understand these conversations and facilitate both human-human and human-machine interactions.
An open source framework for building and deploying Task-Oriented Dialogue (TOD) systems.
view project64% of agents with AI chatbots are able to spend most of their time solving complex problems, versus 50% of agents without AI chatbots.”
Meet the team
Semih Yavuz
Senior Research ScientistSemih conducts research to advance state-of-the-art on NLP with a particular focus on different aspects of conversational AI, question answering, and semantic parsing, while also embedding the AI research developments across Salesforce clouds for customer success.
Latest Publications and News
ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues.
read on arxiv"The Triangle of Trust in Conversational Ethics and Design: Where Bots, Language and AI Intersect" Workshop Summary
learn moreCoCo-DST: Controllable Counterfactuals for Evaluating and Improving Dialogue State Trackers
learn more
Our team is growing!
Salesforce has plenty of conversational applications and opportunities to create high social, product, and research impacts. Apply now and join one of the best AI teams in the world and shape the future of conversational AI with us.
join the team