Online: Efficient Intent Detection with Deep Neural Networks
Hosted by DC Natural Language Processing (DC-NLP)
Details
Ivan Vulić of voice-assistant developer PolyAI (https://www.polyai.com/) and the University of Cambridge will speak on Efficient Intent Detection with Deep Neural Networks.
Abstract: Task-oriented conversational systems allow users to interact with computer applications through conversation in order to solve a particular task with well-defined semantics, such as booking restaurants, hotels and flights, among many others. Intent detection, aiming at understanding the user's current conversational goal, is a vital component of any task-oriented conversational system and often the first point of failure of any conversational agent.
The need for expert domain knowledge and domain-specific labeled data still impedes quick and wide deployment of intent detectors across many sectors, domains, and languages. What is more, such intent detectors, even when they perform well, must remain efficient and scalable to enable deployments in real-world conversational systems.
In this talk, I will thus cover intent detection for dialogue systems from two dual angles: 1) research-based or academic, and 2) production-oriented, also offering insights and know-hows from our work at PolyAI on the development of effective, efficient and production-ready intent detectors. I will address challenges of building such cutting-edge intent detectors, powered by recent advances in deep learning, for a multitude of domains, and in limited low-data scenarios, which are typically met in production when expanding to new sectors, domains, and languages. At the end of the talk, I will also cover some advanced research and work-in-progress topics, including the use of contrastive learning techniques, dealing with voice-based input, and multilingual intent detection.
Bio: Ivan Vulić is a Senior Research Associate in the Language Technology Lab, University of Cambridge and a Senior Scientist at PolyAI. He holds a PhD in Computer Science from KU Leuven awarded summa cum laude. His core expertise is in representation learning, cross-lingual learning, conversational AI, human language understanding, distributional, lexical, multi-modal, and knowledge-enhanced semantics in monolingual and multilingual contexts, transfer learning for enabling cross-lingual NLP applications such as conversational AI in low-resource languages, and machine learning for (cross-lingual and multilingual) NLP.
Ivan has published more than 110 papers at top-tier NLP and IR conferences and journals and has presented numerous tutorial and invited and frequently serves as a program chair and conference organizer.
--
By responding here, you acknowledge and consent to our Code of Conduct: We seek to provide a respectful, friendly, professional experience for everyone regardless of gender, sexual orientation, physical appearance, disability, age, race, and religion. We do not tolerate behavior that is harassing or degrading to any individual, in any form. Participants are responsible for knowing and abiding by these standards. We encourage all attendees to assist in creating a welcoming, safe, and respectful experience.
We are grateful for meetup support provided by Kensho (https://www.kensho.com/), AI & Machine Learning Driving Essential Intelligence, and by John Snow Labs (https://www.johnsnowlabs.com/), publisher of the Spark NLP, an open source text processing library for Python, Java, and Scala.
