Lecture 5: syntax

Introduction to syntax. Context-free grammars and languages. Treebanks. Normal forms. Dependency grammars. Syntactic parsing: top-down and bottom-up. Structural ambiguity. Backtracking vs. dynamic programming for parsing. The CKY algorithm. The Earley algorithm. Probabilistic CFGs (PCFGs). PCFGs for disambiguation: the probabilistic CKY algorithm. PCFGs for language modeling.

Lecture 4: part-of-speech tagging

Introduction to part-of-speech (POS) tagging. POS tagsets: the Penn Treebank tagset and the Google Universal Tagset. Rule-based POS tagging. Stochastic part-of-speech tagging. Hidden markov models. Deleted interpolation. Linear and logistic regression: Maximum Entropy models. Transformation-based POS tagging. Handling out-of-vocabulary words.

Lecture 3: language models and smoothing

The third lecture was about language models. You discovered how important language models are and how we can approximate real language with them. N-gram models (unigrams, bigrams, trigrams) were discussed, together with their probability modeling and issues. We discussed perplexity and its close relationship with entropy, we introduced smoothing and interpolation techniques to deal with the issue of data sparsity.

Lecture 2: morphological analysis and language models

We continued our introduction to regular expressions in Perl. We also introduced finite state transducers for encoding the lexicon and orthographic rules. Today's lecture is about language models. We discussed the importance of language models and how we can approximate real language with them. We introduced N-gram models (unigrams, bigrams, trigrams), together with their probability modeling and issues.

Lecture 1: introduction and morphology (1)

We gave an introduction to the course and the field it is focused on, i.e., Natural Language Processing, with a focus on the Turing Test as a tool to understand whether "machines can think". We also discussed the pitfalls of the test, including Searle's Chinese Room argument.

In the second part, we introduced words and morphemes. Before delving into morphology and morphological analysis, we introduced regular expressions as a powerful tool to deal with different forms of a word.

Homework 1: watch 2001: a Space Odyssey!
Homework 2: read The Hitchhiker's Guide to the Galaxy!

So, you see, you now have two homeworks already...

IMPORTANT: Each lecture will start around 12.55 and end at 4 (with a 10-minute break after about 1 hour 1/2). No lecture on Fridays.

Final course schedule: Thursday 12.45-15.45pm

Pfiuuu! Done! The final course schedule is then Thursday 12.45-15.45pm, in Via Salaria 113, third floor, seminar room (aula seminari)! We will not start before 1pm, so if you are coming from Via Ariosto, take your time. We will discuss the 15-20 min range together!

Please sign up!

The new Google group for the NLP course is now open:

http://groups.google.com/group/naviglinlp2013


IMPORTANT - PLEASE READ: Please sign up by providing in the "You can send additional information to the manager by filling in the text box below." text box:  

First Name, Last Name, Email, Matricola

IMPORTANT 2 - PLEASE READ: I received several emails from the Artificial Intelligence & Robotics M.Sc. degree. I am changing the course schedule. In order to receive further communications about that, please sign up and go to the Doodle poll to provide your course schedule preferences! This will also help me understand how many students will attend and better organize the course and its exam+project.

Ready to start?

Are you ready to start? The course will most likely start on March 5 with exciting news and a new pragmatic structure (more information soon).

Lecture 21: Statistical Machine Translation (2/2) (8/6/12)

IBM models for word alignment. Many-to-one and many-to-many alignments. IBM model 1 and the HMM alignment model. Training the alignment models: the Expectation Maximization (EM) algorithm. Symmetrizing alignments for phrase-based MT: symmetrizing by intersection; the growing heuristic. Calculating the phrase translation table. Decoding: stack decoding. Evaluation of MT systems. BLEU. Log-linear models for MT.

Lecture 20: Statistical Machine Translation (1/2) (5/6/12)

Introduction to Machine Translation. Rule-based vs. Statistical MT. Statistical MT: the noisy channel model. The language model and the translation model. The phrase-based translation model. Learning a model of training. Phrase-translation tables. Parallel corpora. Extracting phrases from word alignments. Word alignments.