Tutorial 14: Graph-based Semi-Supervised Learning Algorithms for Speech & Spoken Language Processing

Monday, May 27, 2-5 pm

Presented by

Amarnag Subramanya, Partha Pratim Talukdar

Abstract

The tutorial is divided in two parts. In the first part, we will motivate the need for graph-based Semi-supervised Learning (SSL) methods, introduce some standard graph-based SSL algorithms, and discuss connections between these approaches. Graph construction is a key ingredient in the success of graph-based SSL methods. To this end, we will discuss how speech & linguistic data can be represented via graphs, and approaches to automatically construct such graphs. We will also show how graph-based algorithms can be scaled to large amounts of data (e.g., web-scale data).

Part 2 of the tutorial will focus on how graph-based methods can be used to solve several problems in speech & NLP, including problems such as phonetic classification, PoS tagging, text categorization, information acquisition, and word sense disambiguation. We will conclude the tutorial with some exciting avenues for future work. Familiarity with semi-supervised learning and graph-based methods will not be assumed, and the necessary background will be provided. Lessons learned from using graph-based algorithms to solve real-world problems will be used throughout the tutorial to convey the necessary concepts. At the end of this tutorial, the attendee will walk away with the following:

  • An in-depth knowledge of the current state-of-the-art in graph-based SSL algorithms, and the ability to implement them.
  • The ability to decide on the suitability of graph-based SSL methods for a problem.
  • Familiarity with different speech & NLP tasks where graph-based SSL methods have been successfully applied.

Homepage

Tutorial Outline:

  • Introduction
    • Why graph-based SSL methods?
    • Graph construction from speech & linguistic data
  • Graph-based SSL methods
    • Regularization-based methods
  • Scaling to large data
  • Applications
    • Phone Classification
    • PoS Tagging
    • Word sense disambiguation
    • Text Categorization
    • Statistical Machine Translation (SMT)
  • Conclusion
    • Open problems

Speaker Biography

Amarnag Subramanya

Google Research
1600 Amphitheater Pkwy.
Mountain View, CA 94043
Email: asubram@google.com
Web: http://sites.google.com/site/amarsubramanya

Amarnag Subramanya is a Senior Research Scientist in Machine Learning & Natural Language Processing at Google Research. Amarnag received his PhD (2009) from the University of Washington, Seattle, working under the supervision of Jeff Bilmes. His research interests include machine learning and graphical models. In particular he is interested in the application of semi-supervised learning to large-scale problems in speech & natural language processing. His dissertation focused on improving the performance and scalability of graph-based semi-supervised learning algorithms for problems in speech, natural language, and vision. He was the recipient of the Microsoft Research Graduate fellowship in 2007. He co-organized a session on "Semantic Processing" at the 2011 National Academy of Engineering's (NAE) Frontiers of Engineering (USFOE) conference.

Partha Pratim Talukdar

GHC 8133, Machine Learning Department
Carnegie Mellon University
5000 Forbes Ave., Pittsburgh, PA 15213
Email: partha.talukdar@cs.cmu.edu
Web: http://www.talukdar.net

Partha Pratim Talukdar is a Postdoctoral Fellow in the Machine Learning Department at Carnegie Mellon University, working with Tom Mitchell on the NELL project. Partha received his PhD (2010) in CIS from the University of Pennsylvania, working under the supervision of Fernando Pereira, Zack Ives, and Mark Liberman. Partha is broadly interested in Machine Learning, Natural Language Processing, and Data Integration, with particular interest in large-scale learning and inference over graphs. His dissertation introduced novel graph-based weakly-supervised methods for Information Extraction and Integration. His past industrial research affiliations include HP Labs, Google Research, and Microsoft Research. Partha was a co-organizer of the NAACL-HLT 2012 workshop on web-scale knowledge extraction from text (AKBC-WEKEX 2012), and an Area Co-Chair for EMNLP-CoNLL 2012.