Fall 2017

Monday 5:10-7:00

60 Fifth Avenue [Forbes Building], Room C12

This version posted 17 August 2017.

60 Fifth Avenue [Forbes Building], Room 300

phone: 998-3497

email: grishman@cs.nyu.edu

Fall office hours: Mondays, 2:30-3:30 PM

(generally also available Mondays 11:00-1:00 and Thursdays 11:00-12:00; please send an email in advance if possible)

Good programming skills.

Knowledge of Java.

- deliver baseline component [brief class presetation] (due: class 4)
- enhance your component [brief class presetation] (due: class 7)
- Markov Logic Network assignment (due: class 9)
- conduct experiment involving joint inference, deep learning, or domain modeling (due: class 13; class presentation week 14)
- (2) class presentations of papers

As a general reference for most of the topics covered in the course we recommend Jurafsky and Martin's

slides | notes | |
---|---|---|

1 (Sept. 11) |
Preliminaries JetLite Tokenizer |
JetLite Tokenizer bibliography |

2 (Sept. 18) |
Maximum Entropy Named Entity tagging |
NamedEntity references |

3 (Sept. 25) |
Evaluation in jetLite Coref tagging |
Coreference references |

4 (Oct. 2) | Relation tagging | Relation extraction references |

5 (Oct. 16) | Entity and Event tagging | Entity and Event tagging references |

6 (Oct. 23) | Joint Inference and Belief Propagation | Joint Inference and Belief Propagation references |

7 (Oct. 30) | Student Status Reports | |

8 (Nov. 6) |
Joint Inference, cont'd
Markov Logic Networks |
Joint Inference, cont'd
code for Belief Propagation |

9 (Nov. 13) | Markov Logic Networks | Alchemy |

10 (Nov. 20) |
Markov Logic Networks (assignment) |