Lecture 10: 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. Log-linear models for MT.

Lecture 9: Semantic Role Labeling, Discourse and Advanced Topics

Semantic Fields. The semantics of events. Semantic roles. Thematic Roles. FrameNet. Semantic restrictions and preferences. Semantic Role Labeling. Features. The state of the art.

Discourse: computational discourse. Motivating examples. Unsupervised vs. supervised linear segmentation. Text coherence. Automatic coherence assignment. Reference resolution. Pronominal Anaphora Resolution.

Advanced topic: Multilingual unsupervised Part-of-Speech Tagging.

Lecture 8: NLP Research at Sapienza

Maud Ehrmann: Acronym extraction. Stefano Faralli: Ontology Learning from scratch. Tiziano Flati: automatic harvesting of semantic predicates. Marc Franco Salvador: plagiarism detection. David Jurgens: Gathering annotated data and Relational similarity. Andrea Moro: Semantically-Enhanced Open Information Extraction. Taher Pilehvar: Textual similarity. Daniele Vannella: Word Sense Induction.

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. The Senseval and SemEval evaluation competitions. Applications of Word Sense Disambiguation. Issues: representation of word senses, domain WSD, the knowledge acquisition bottleneck.
 

Lecture 6: 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.