with our free apps for iPhone, iPad and Android

Get StartedAlready have an account? Log In

Natural Language Processing and
Applications
by Thomas Breuel
# Natural Language Processing and
Applications

## outline

### 1

### 2

### 3

### 4

### 5

### 6

### 7

### 8

### 9

### 10

### 11

### 12

## not covered

### lexical acquisition

### probabilistic context free grammars

### probabilistic parsing

### clustering

## exam preparation

### after each lecture...

### identify definitions and concepts

### identify mathematical proofs and derivations
that were covered

### identify algorithms that were covered

### identify major concepts/tools that were
covered

### make a written list of definitions, concepts,
proofs, derivations, and algorithms that you
studied and bring them to the oral exam

### during the exam

## reading

### Manning and Schütze: Foundations of
Statistical NLP

### Bird and Klein: Natural
Language Processing in Python

### Perkins: Python Text Processing with
NLTK 2.0 Cookbook

### Russell: Mining the Social Web (additional
reading)

## course mechanics

### lectures: Room 48-462 Time Wednesdays,
1:45 - 3:15 pm

### exercises: TBD

### exam: oral

### office hours

### http://nlpa.iupr.com/

## exercises

### required for taking the oral exam

### bring the completed exercises with you to the
oral exam (otherwise you can't take the exam)

### Exercises are mostly in Python, with some
theory.

### Do your exercises in iPython notebooks and
hand them in.

### Many exercises will give you a Python
notebook as a starting point.

## presentation on application
examples

0.0 stars - reviews
range from 0 to 5

overview of applications

linguistic essentials, history of language, language variation, basic grammatical concepts

exercise: review grammar, refresh Python

UNIX command line tools

some Python

mathematical foundations, probability theory, common distributions, Bayesian methods, information theory

corpora, what are corpora and how are they used?, what corpora are available?, tokenization, lemmatization, stemming, markup, tagging

n-gram models, collocations, statistical models, sparsity, smoothing, back-off, cross-validation and testing

markov models

finite state transducers

CRFs

discriminative language models

text classification and clustering

recurrent neural networks

statistical alignment and MT

word sense disambiguation

parts-of-speech tagging

For any definition/concept, you should be able to give a concise and clear definition in the exam

For any derivation that we covered in class or the exercises, you should be able to repeat it in the exam and also solve similar problems.

For any covered algorithm, you should be able to state the inputs/outputs, and the sequence of steps.

You also need to be able to demonstrate that you know the tools that have been used in the exercises (UNIX/POSIX command line tools, Python)

make appointments with secretary@iupr.com

course assistants, TBD

professor, make appointment with secretary@iupr.com