Instructor: Dr. Yoav Goldberg
Email: yogo / cs.biu.ac.il
Office: 216 building 216
Office Hours: TBA
This seminar course introduces current methods in structure-prediction for NLP.
Students are required to read research papers and present them in class, as well as implement one of the methods discussed in class. The grade will be based on class participation, quality of presentation, and the implementation project.
Please sign up over email for the paper you'd like to present.
Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms
/ Michael Collins
Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data
/ Yoshimasa Tsuruoka and Jun'ichi Tsujii
Semi-Markov Conditional Random Fields for Information Extraction
/ Sunita Sarawagi and William W. Cohen
Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling
/ Jenny Rose Finkel, Trond Grenager, and Christopher Manning
Spanning Tree Methods for Discriminative Training of Dependency Parsers
/ Ryan McDonald, Koby Crammer and Fernando Pereira
Incremental Integer Linear Programming for Non-projective Dependency Parsing
/ Sebastian Riedel and James Clarke
Deterministic Dependency Parsing of English Text
/ Joakim Nivre and Mario Scholz
A Tale of Two Parsers: investigating and combining graph-based and transition-based dependency parsing using beam-search
/ Yue Zhang and Stephen Clark
An efficient algorithm for easy-first non-directional dependency parsing
/ Yoav Goldberg and Michael Elhadad
TBA
When you prepare your presentation, try to keep in mind the following questions: