Friday, March 16, 2018

Lecture 6 (16/03/2018): deep learning and word embeddings (1)

Introduction to neural networks. The perceptron. Neural units. Activation functions. MaxEnt and softmax. Word embeddings: rationale and word2vec. CBOW and skipgram. Homework 1 assignment!

Lecture 5 (15/03/2018): 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

Friday, March 9, 2018

Lecture 4 (09/03/2018): TensorFlow for linear and polynomial regression; TensorBoard

More on TensorFlow: variables, placeholders, sessions, training. Linear and polynomial regression. TensorBoard.

Lecture 3 (08/03/2018): introduction to Machine Learning for NLP / TensorFlow

Introduction to Machine Learning for Natural Language Processing: supervised vs. unsupervised vs. reinforcement learning. Features, feature vector representations. TensorFlow.

Friday, March 2, 2018

Lecture 2 (02/03/2018): Introduction to NLP (2)

We continued our introduction to NLP, 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.

Lecture 1 (01/03/2018): Introduction to NLP (1)

We gave an introduction to the course and the field it is focused on, i.e., Natural Language Processing.

Wednesday, January 17, 2018

Ready, steady, go!

Welcome to the Sapienza NLP course blog! This year there will be important changes:

  1. You will write a paper 
  2. The course will be much more deep learning oriented
  3. For attending students, there will be only three homeworks (and no additional duty), one of which will be done with delivery by the end of September and will replace the project. Non-attending students, instead, will have to work on a full-fledged project.

IMPORTANT: The 2018 class hour schedule will be on Thursday 16.30-19 and Fridays 14.00pm-16.30pm, Aula 2 - Aule L ingegneria.

Please sign up to the NLP class!

Saturday, May 27, 2017

Lecture 13: semantic parsing; statistical and neural machine translation

Semantic parsing: supervised, unsupervised, semi-supervised. FrameNet. Abstract Meaning Representations.

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. Neural MT: the encoder-decoder architecture; advantages; results.

Friday, May 19, 2017

Lecture 12: Entity linking; semantic similarity; sense embedding; semantic parsing; project presentation

Entity Linking. Main approaches. AIDA, TagMe, Wikifier, DBpedia spotlight, Babelfy. The MASC annotated corpus. Semantic similarity. Sense embeddings. Project presentation.

Friday, May 12, 2017

Lecture 11: 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, IMS with embeddings, neural approaches to WSD. 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. Entity Linking.