|
Week
|
Lecture (Thursday)
|
Links
|
Week 1:
|
Everything you ever wanted to know about computational linguistics, in one class!
(a.k.a. Course Overview)
Introduction to Information Retrieval
Reading: Chapters 1 and 2 of the Introduction to Information Retrieval
|
Course Syllabus
Open NLP Project
LingPipe Project
|
Week 2:
|
Information Retrieval
Reading: Chapters 6 and 12 of the Introduction to Information Retrieval
|
Snowball Stemming Software
Apache Lucene Open-source Search Engine
Lemur Project
|
Week 3:
|
Introduction to Text Classification with logistic regression
Reading: Chapters 13, 14, and 15 of the Introduction to Information Retrieval
|
SVM Light
LibSVM
MALLET Project (includes MaxEnt, Naive Bayes, other things)
Hal Daume's MaxEnt software
|
Week 4:
|
SVD, LSI, LDA --- acronyms, oh my!
Reading: Chapter 18 of the Introduction to Information Retrieval
and Latent Dirichlet Allocation
|
|
Week 5:
|
Information Extraction 1
Reading: Unsupervised Named-Entity Extraction from the Web
(read everything, but skim sections 3-5)
|
|
Week 6:
|
Ngrams, Markov models, and Hidden Markov Models
Reading:
Joshua Goodman's Tutorial on Ngram Models
(Read sections 1 and 3, and the Kneser-Ney Smoothing portion of section 2. Check out the rest if it interests you.)
HMM Tutorial (Read sections 1-3.)
|
Joshua Goodman's PPT Tutorial on Ngram Models
SRI Language Modeling Toolkit
Java HMM software
|
Week 7:
|
Supervised Sequence Labeling
Reading:
CRF Tutorial
|
Java CRF package
|
Week 8:
|
Advanced Topics 1: Representations and Domain Adaptation
Reading:
Distributional Representations for Handling Sparsity in Supervised Sequence Labeling
Exploring Representation-Learning Approaches to Domain Adaptation
|
|
Week 9:
|
Midterm and Projects
|
|
Week 10:
|
Grammar and Parsing
Reading:
C.D. Manning & H. Schuetze, Foundations of Statistical Natural Language Processing, Cambridge: MIT Press, 1999
Chapters 11 and 12.1.1-12.1.4, 12.1.7, and 12.1.8 (available online free if accessed from Temple computers)
|
Stanford Parser
|
Week 11:
|
Parsing (continued) and Grammar Induction
Reading:
Corpus-Based Induction of Syntactic Structure
|
|
Week 12:
|
Shallow Semantics
Reading: Dan Gildea's Semantic Role Labeling paper (Read sections 1-6)
|
SwiRL, Mihai Surdeanu's GPL semantic role labeling software
UIUC's semantic role labeling demo
|
Week 13:
|
Semantics
Reading:
An introduction to formal computational semantics
Parsing to Logical Form
|
|
Week 14:
|
Question Answering
Reading:
Building Watson: An Overview of the DeepQA Project
|
|
Week 15:
|
Final Project Report due on Monday, May 10 at 6p.m.!
|
|