Keynotes

Keynote 1

Title

How Many Multiword Expressions do People Know?

Speaker

Dr. Kenneth Church

Abstract

What is a multiword expression (MWE) and how many are there? What is a MWE? What is many? Mark Liberman gave a great invited talk at ACL-89 titled “How many words do people know?” where he spent the entire hour questioning the question. Many of these same questions apply to multiword expressions. What is a word? What is many? What is a person? What does it mean to know? Rather than answer these questions, this paper will use these questions as Liberman did, as an excuse for surveying how such issues are addressed in a variety of fields: computer science, web search, linguistics, lexicography, educational testing, psychology, statistics, etc

For BIo see http://researcher.ibm.com/view.php?person=us-kwchurch 

For publications/citations, see http://scholar.google.com/citations?user=E6aqGvYAAAAJ&hl=en

Keynote 2

Title

Deep Learning and A New Wave of Innovations in Speech Technology

Speaker

Professor Li Deng

Abstract

Semantic information embedded in the speech signal manifests itself in a dynamic process rooted in the deep linguistic hierarchy as an intrinsic part of the human cognitive system. Modeling both the dynamic process and the deep structure for advancing speech technology has been an active pursuit for over more than 20 years, but it is not until recently that noticeable breakthrough has been achieved by the new methodology commonly referred to as “deep learning”. Deep Belief Net (DBN) and the related deep neural nets are recently being used to replace the Gaussian Mixture Model component in the HMM-based speech recognition, and has produced dramatic error rate reduction in both phone recognition and large vocabulary speech recognition while keeping the HMM component intact. On the other hand, the (constrained) Dynamic Bayesian Net has been developed for many years to improve the dynamic models of speech while overcoming the IID assumption as a key weakness of the HMM, with a set of techniques and representations commonly known as hidden dynamic/trajectory models or articulatory-like models. A history of these two largely separate lines of research will be critically reviewed and analyzed in the context of modeling the deep and dynamic linguistic hierarchy for advancing speech recognition technology. Future directions will be discussed for the exciting area of deep and dynamic learning research that holds promise to build a foundation for the next-generation speech technology with human-like cognitive ability.