Lecture 12: statistical machine translation

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. 

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.

Lecture 11: semantic parsing (2), AMR, research in Rome

Unsupervised semantic parsing, semi-supervised semantic parsing, Abstract Meaning Representation (AMR). NLP research in Rome.

Lecture 10: semantic role labeling and semantic parsing

PropBank, FrameNet, semantic role labeling. Introduction to semantic parsing. Presentation of the projects.

Lecture 9: Neural Networks, word embeddings and deep learning

Motivation. The perceptron. Input encoding, sum and activation functions; objective function. Linearity of the perceptron. Neural networks. Training. Backpropagation. Connection to Maximum Entropy. Connection to language. Vector representations. NN for the bigram language model. Word2vec: CBOW and skip-gram. Word embeddings. Deep learning. Language modeling with NN. The big picture.

Lecture 8: Entity Linking

Entity Linking. Main approaches. AIDA, TagMe, Wikifier, DBpedia spotlight, Babelfy. The MASC annotated corpus. Demo di sistemi di WSD e Entity Linking. Introduction to Neural Networks.

Lecture 7: Word Sense Disambiguation

Introduction to Word Sense Disambiguation (WSD). Motivation. The typical WSD framework. Lexical sample vs. all-words. WSD viewed as lexical substitution and cross-lingual lexical substitution. Knowledge resources. Representation of context: flat and structured representations. Main approaches to WSD: Supervised, unsupervised and knowledge-based WSD. Two important dimensions: supervision and knowledge. Supervised Word Sense Disambiguation: pros and cons. Vector representation of context. Main supervised disambiguation paradigms: decision trees, neural networks, instance-based learning, Support Vector Machines. Unsupervised Word Sense Disambiguation: Word Sense Induction. Context-based clustering. Co-occurrence graphs: curvature clustering, HyperLex. Knowledge-based Word Sense Disambiguation. The Lesk and Extended Lesk algorithm. Structural approaches: similarity measures and graph algorithms. Conceptual density. Structural Semantic Interconnections. Evaluation: precision, recall, F1, accuracy. Baselines.

Lecture 6: computational semantics

Introduction to computational semantics. Syntax-driven semantic analysis. Semantic attachments. First-Order Logic. Lambda notation and lambda calculus for semantic representation. Lexicon, lemmas and word forms. Word senses: monosemy vs. polysemy. Special kinds of polysemy. Computational sense representations: enumeration vs. generation. Graded word sense assignment. Encoding word senses: paper dictionaries, thesauri, machine-readable dictionary, computational lexicons. WordNet. Wordnets in other languages. BabelNet.

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. Demo: The Stanford Dependency parser.

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. The Stanford POS tagger.

Lecture 3: language modeling

We introduced N-gram models (unigrams, bigrams, trigrams), 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. The KYOTO and Berkley Language Model toolkits.

We also discussed the homework 1 in more detail (see slides on the class group).

Lecture 2: morphological analysis

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. We then introduced recent work on morphological analysis based on pattern generalization. We assigned homework 1 for Wiktionary-based morphological analysis.

Lecture 1: introduction

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. We then provided examples of tasks in desperate need for accurate NLP: computer-assisted and machine translation, text summarization, personal assistance, text understanding, machine reading, question answering, information retrieval.

Ready, steady, go (with news!!!)

Welcome to the Sapienza NLP course blog! This year there will be important changes: first, projects will be lightweight for attending students; second, homeworks will be part of the final project. In this respect, attending students will complete more than 50% of their projects before the end of the course.
IMPORTANT: The 2016 class hour schedule will be on Fridays 2.30pm-5.45pm. Please sign up to the NLP class!