Schema della sezione
-
Schedule Day Hour Room Monday 11-13 L1, Polo Fibonacci Tuesday 9-11 C1, Polo Fibonacci Friday 14-16 A1, Polo Fibonacci Jupyter Notebook Server
A server has been setup for running Jupyter Notebooks. You can log into the server with your University credentials for Google GSuite.
-
Date
Topic
Material
18/2/2019 Introduction slides 20/2/2018 Language Models slides
Suggested readings:- SLP, Chapter 3.
23/2/2018 Language Models slides 26/2/2018 Word Vectors slides
Suggested readings:
27/2/2018 Word Vectors slides 4/3/2018 Text Classification slides
Suggested readings:- SLP Chapter 6
5/3/2018 Tokenization slides
1/3/2018 Introduction to Python and NLTK See notebooks: 9/3/2018 Preprocessing text slides
Suggested readings:- SLP Chapter 2
12/3/2018 Hidden Markov Models slides
Suggested readings:- SLP Chapter 9
16/3/2018 Deep Learning for NLP slides
Suggested readings:- R. Collobert et al. 2011. Natural Language Processing (Almost) from Scratch. Journal of Machine Learning Research
19/3/2018 Keras slides
See notebooks:- MNIST/MNIST%20in%20Keras.ipynb
- HLT/RNN-Tagger-keras.ipyn
22/3/2018 Dependency Parsing slides
Further readings:- Joakim Nivre. 2004. Incrementality in Deterministic Dependency Parsing. Workshop on Incremental Parsing.
- Danqi Chen and Christopher D. Manning. 2014. A Fast and Accurate Dependency Parser using Neural Networks. EMNLP 2014.
- Sandra Kübler, Ryan McDonald, Joakim Nivre. 2009. Dependency Parsing. Morgan and Claypool.
- Daniel Andor, Chris Alberti, David Weiss, Aliaksei Severyn, Alessandro Presta, Kuzman Ganchev, Slav Petrov, and Michael Collins. 2016. Globally Normalized Transition-Based Neural Networks. ACL 2016.
- Marie-Catherine de Marneffe, Timothy Dozat, Natalia Silveira, Katri Haverinen, Filip Ginter, Joakim Nivre, and Christopher D. Manning. 2014. Universal Stanford Dependencies: A cross-linguistic typology. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC-2014). Revised version for UD v1.
- Universal Dependencies website
25/3/2018 Neural Dependency Parsing 29/3/2018 Universal Dependencies slides
26/3/2018 Sentiment Analysis slides
27/3/2018 Sentiment Analysis: Lexical Resources slides
13/4/2018 Sentiment Analysis on Tweets: Semeval 2013-14 slides
Further readings:16/4/2018 Sentiment Analysis on Tweets: SemEval 2015-17 slides
Further readings:17/4/2018 Solution to Homework 1 See Jupyter Notebook HLT/HW1/Solution.ipynb
20/4/2018 Solution to Homework 1
POS Tagging, ParsingSee Jupyter Notebook HLT/HW1/Solution.ipynb
20/4/2018 Recurrent Neural Networks slides
See Jupyter Notebook HLT/HW1/POS Tagger with LSTM.ipynb
Further readings:24/4/2018 Neural Networks with Memory slides 27/4/2018 Neural Networks with Memory and Attention slides 30/4/2018 Dynamic Neural Networks slides 2/5/2018 Deep Learning for Question Answering slides
Further readings:4/5/2018 Machine Translation slides 7/5/2018 Phrase Based Statistical Machine Translation slides 8/5/2018 Neural Machine Translation slides 11/5/2018 Introduction to TensorFlow slides 14/5/2018 Coreference Resolution slides 15/5/2018 Project Suggestions slides 18/5/2018 Chatbots slides
Further readings:21/5/2018 Reinforcement Learning slides 22/5/2018 Semi-supervised Learning for NLP See Kevin Clark's presentation. 25/5/2018 Future of NLP slides 28/5/2018 Discussion and progress report on projects - SLP, Chapter 3.
-
- D. Jurafsky, J.H. Martin, Speech and Language Processing. 3rd edition, Prentice-Hall, 2018.
- B. Liu, Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012.
- S. Kubler, R. McDonald, J. Nivre. Dependency Parsing. 2010.
- P. Koehn. Statistical Machine Translation. Cambridge University Press, 2010.
- S. Bird, E. Klein, E. Loper. Natural Language Processing with Python.
Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016.
- D. Jurafsky, J.H. Martin, Speech and Language Processing. 3rd edition, Prentice-Hall, 2018.
-
- Deep Learning for NLP, Stanford.