Natural Language Processing - AA 2018/2019
Prof. Licia Sbattella
Slides "Voice and prosody" added to the Voice section.
Added slides on Coherence and Anaphora resolution. Sorry for the delay.
Fixed an error in slide 45 of "Speech processing - Automatic Speech Recognition and Text To Speech".
Extra call: Monday 2018-11-5; 16:15; classroom L.26.11.
I modify a bit the parser code, to stress that the parse tree with maximum probability could be wrong.
Please find below the slides about TTS-ASR. For those who attended the lecture: I removed the final slides, so the topic is over.
If you use Jupyter, please find below the notebook I used today.
Laboratory 2018-10-17: please, install Python3 (this is mostly for Windows; in Linux and macOS Python3 should be already there); then install NLTK, and Numpy (see: Installing NLTK); finally, do not forget to Install NLTK Data. Please, come with your own laptop (student pairs can share a laptop). We can't provide power strips, so be sure your laptops are fully charged. I also suggest to download an IDE of your choice.
Slightly modified versions of slides "Error correction, prediction, n-grams", "Parsing", and "Shallow parsing, probabilistic parsing" have been uploaded.
Slide #8 of "Error correction, prediction, n-grams" has been fixed.
Date of the extra call.
Dates of laboratory sessions.
Web site is on-line.
Prof. Licia Sbattella
Ing. Roberto Tedesco:
- Slides shown during lectures.
- Most of the course slides are based on the book: D. Jurafsky and J. H. Martin, Speech and Language Processing, 2nd edition.
- Another useful book: C. D. Manning and H. Schuetze, Foundations of Statistical Natural Language Processing.
- Introduction to the NLTK toolkit (version 3): S. Bird, E. Klein, and E. Loper: Natural Language Processing with Python (look at the HTML version)
- How to take exams:
- Exam is written and lasts 2h30min.
- Exam is composed of 3 topics, each composed of 3 questions (9 questions in total).
- Among such questions, you could find one or two simple exercises (drawing simple parse trees, calculate simple formulas about smoothing, etc.); you do not need any calculator.
- Whenever you want to attend an exam, or need to register your final mark, you must enroll. PLEASE, DO NOT FORGET TO ENROLL TO THE CALLS. NO EXCEPTIONS WILL BE CONSIDERED!
- Laboratory sessions. Four lab sessions will give you extra points; signatures will be collected.
- Wednesday 2018-9-26 - 10.15 to 13.15 - classroom D.2.2
- Wednesday 2018-10-17 - 10.15 to 13.15 - classroom D.2.2
- Wednesday 2017-10-24 - 10.15 to 12.15 - classroom D.2.2
- Wednesday 2017-10-31 - 10.15 to 13.15 - classroom D.2.2
- Extra call: Monday 2018-11-5; 16:15; classroom L.26.11.
Download course materials
Words (morphology, error correction, prediction, n-grams)
POS tagging, syntactic analysis
Neural Networks and NLP
At the ARCSLab laboratory, students and researchers study models ad technologies related to the development of adaptive and relational systems.
Research topics include:
Theses are available on such topics! Have a look!
- Multi-channel access to web services and information
- Multimodal communication and storytelling
- Virtual contexts for rehabilitation and education
- NLP, including speech analysis and voice processing
- Particular attention is given to applications for fragility, disease and disability