Strumenti Utente

Strumenti Sito


magistraleinformatica:eln:start

Questa è una vecchia versione del documento!


Elaborazione del Linguaggio Naturale

Laurea Magistrale: Informatica.

Docente: Giuseppe Attardi Ricevimento: Mercoledì, 11:00

Schedule
Day Hour Room
Tuesday 9-11 C, Polo Fibonacci
Friday 14-16 C, Polo Fibonacci

Prerequisiti

  1. Calcolo delle probabilità e statistica
  2. Programmazione

Programma

  1. Introduction
    1. History
    2. Present and Future
    3. NLP and the Web
  2. Mathematical Background
    1. Probability and Statistics
    2. Language Model
    3. Hidden Markov Model
    4. Viterbi Algorithm
    5. Generative vs Discriminative Models
  3. Linguistic Essentials
    1. Part of Speech and Morphology
    2. Phrase structure
    3. Collocations
    4. n-gram Models
    5. Word Sense Disambiguation
  4. Preprocessing
    1. Encoding
    2. Regular Expressions
    3. Segmentation
    4. Tokenization
    5. Normalization
  5. NLTK
    1. Introduction to Python
    2. Overvies of NLTK libraries
  6. Classification
    1. Machine Learning
    2. Statistical classifiers
      1. Bayesan Network
      2. Perceptron
      3. Maximum Entropy
      4. Support Vector Machines
      5. Hidden Variable Models
  7. Clustering
    1. K-means
    2. Factored Models
      1. Singular Value Decomposition
      2. Latent Semantic Indexing
  8. Tagging
    1. Part of Speech
    2. Named Entity
    3. Super Senses
  9. Sentence Structure
    1. Constituency Parsing
    2. Dependency Parsing
  10. Semantic Analysis
    1. Semantic Role Labeling
    2. Coreference resolution
  11. Statistical Machine Translation
    1. Word-Based Models
    2. Phrase-Based Models
    3. Decoding
    4. Syntax-Based SMT
    5. Evaluation metrics
  12. Processing Pipelines
    1. Integrated tooolkit
    2. Frameworks
      1. Gate
      2. UIMA
    3. Data Pipeline
      1. Tanl
  13. Applications
    1. Information Extraction
    2. Information Filtering
    3. Recommender System
    4. Opinion Mining
    5. Semantic Search
    6. Question Answering
      1. Text Entailment

Lecture Notes

Date Lecture Notes
21/2/2014 L'età della parola
25/2/2014 Introduction 1-intro.pptx
28/2/2014 Introduction to probability (slides)
4/3/2014 Python Tutorial (slides) Python: Functionals and Generators
7/3/2014 Text Classification (slides)
11/3/2014 Naive Bayes Classifier
14/3/2014 Introduction to NLTK (slides)
18/3/2014 Segmentation and Tokenization (slides) Homework 1
21/3/2014 Maximum Entropy Models (slides) Homework n. 2
25/3/2014 Hidden Markov Model (slides)
28/3/2014 Named Entity Recognition (slides)
8/4/2014 Perceptron, SVM8-classifiers.ppt
11/4/2014 Dependency Formalism(slides)
15/4/2014 Dependency Parsing (Graph Based , Transition Based)
29/4/2014 Relation Extraction 12-relextraction.ppt
2/5/2014 Sentiment Analysis13-opinionmining.ppt
6/5/2014 State of the Art in Sentiment Analysis of Tweets NRC Canada at SemEval 2013
9/5/2014 Deep Learning Deep Learning Tutorial at NAACL 2013
13/5/2014 Deep Learning for Sentiment Analysis
16/5/2014 Machine Translation (MT)
20/5/2014 Phrase Based Statistical Machine Translation (PBMT)
Summarization Summarization
Automatic Speech Recognition ASR Overview

Temi di Approfondimento

Testi di riferimento

  1. C. Manning, H. Schutze. Foundations of Statistical Natural Language Processing. MIT Press, 2000.
  2. D. Jurafsky, J.H. Martin, Speech and Language Processing. 2nd edition, Prentice-Hall, 2008.
  3. S. Kubler, R. McDonald, J. Nivre. Dependency Parsing. 2010.
  4. P. Koehn. Statistical Machine Translation. Cambridge University Press, 2010.
  5. S. Bird, E. Klein, E. Loper. Natural Language Processing with Python.

Modalità di esame

Progetto e orale.

Progetti Evalita 2014

Corsi affini

  1. Apprendimento Automatico: Fondamenti
  2. Data Mining: fondamenti
  3. Information Retrieval
  4. Sistemi Basati sulla Conoscenza

Edizioni Precedenti

magistraleinformatica/eln/start.1400671809.txt.gz · Ultima modifica: 21/05/2014 alle 11:30 (7 anni fa) da Giuseppe Attardi