Questa è una vecchia versione del documento!
<html> <!– Google Analytics –> <script type=“text/javascript” charset=“utf-8”> (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','www.google-analytics.com/analytics.js','ga'); ga('create', 'UA-34685760-1', 'auto', 'personalTracker', {'allowLinker': true}); ga('personalTracker.require', 'linker'); ga('personalTracker.linker:autoLink', ['pages.di.unipi.it', 'enforce.di.unipi.it', 'didawiki.di.unipi.it', 'luciacpassaro.github.io'] ); ga('personalTracker.require', 'displayfeatures'); ga('personalTracker.send', 'pageview', 'courses/txa/'); setTimeout(“ga('send','event','adjusted bounce rate','30 seconds')”,30000); </script> <!– End Google Analytics –> <!– Global site tag (gtag.js) - Google Analytics –> <script async src=“https://www.googletagmanager.com/gtag/js?id=G-LPWY0VLB5W”></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'G-LPWY0VLB5W'); </script> <!– Capture clicks –> <script> jQuery(document).ready(function(){ jQuery('a[href$=“.pdf”]').click(function() { var fname = this.href.split('/').pop(); ga('personalTracker.send', 'event', 'TXA', 'PDFs', fname); }); jQuery('a[href$=“.r”]').click(function() { var fname = this.href.split('/').pop(); ga('personalTracker.send', 'event', 'TXA', 'Rs', fname); }); jQuery('a[href$=“.zip”]').click(function() { var fname = this.href.split('/').pop(); ga('personalTracker.send', 'event', 'TXA', 'ZIPs', fname); }); }); </script> </html> ====== Text Analytics (635AA) A.Y. 2023/24 ====== ==== Teacher ==== Laura Pollacci (laura.pollacci [at] di [dot] unipi [dot] it) Office hours: ==== Schedule ==== ^ Day ^ Hour ^ Room ^ | Thursday | 16-18 | Fib C1 | | Friday| 11-13 | Fib M1 | Team of the class ==== Objectives ==== The course targets text analytics systems and applications to respond to business problems by discovering and presenting knowledge that is otherwise locked in textual form. The main objectives of the course are: - Learning essential techniques, algorithms, and models used in natural language processing. - Understanding of the architectures of typical text analytics applications and of libraries for building them. - Expertise in design, implementation, and evaluation of applications that exploit analysis, interpretation, and transformation of texts. ==== Background ==== * Background: Natural Language Processing, Information Retrieval and Machine Learning * Mathematical background: Probability, Statistics and Algebra * Linguistic essentials: words, lemmas, morphology, Part of Speech (PoS), syntax * Basic text processing: regular expression, tokenisation * Data collection: scraping * Basic modelling: collocations, language models * Introduction to Machine Learning: theory and practical tips * Libraries and tools: NLTK, Spacy, Keras, pytorch * Classification/Clustering * Sentiment Analysis/Opinion Mining * Information Extraction/Relation Extraction/Entity Linking * Transfer learning * Quantification ==== Lecture Notes ==== ^ Date ^ Lecture ^ Slides ^ Material / Reference ^ | 2023/09/21 | Introduction to the course, NLP & Text Analytics. | 1 - Introduction to the Text Analytics course|J. Eisenstein. Introduction to Natural Language Processing. MIT Press. Chp. 1.| | 2023/09/22 | Reminds on probability. | 2 - Reminds on probability| | 2023/09/28 | Introduction to Python. | 3 - Introduction to Python| L3 - Introduction_to_Python.ipynb | | 2023/09/29 | Introduction to Python - part 2. Project and Dates | 4 - Project and Dates| | 2023/10/05 | Probabilistic language models| 5 - Probabilistic language models| D. Jurafsky, J.H. Martin. Ch3 L5 Probabilistic Language Model.ipynb | | 2023/10/06| Text Indexding: Strings, Regular Expressions and BS4. | 6 - Text indexing 1 | D. Jurafsky, J.H. Martin. Ch2 L6.1 - Strings Regular expressions and BS4.ipynb| | 2023/10/12| Linguistic annotation. NLTK. | 6 - Text Indexing 2|L6.2 - Linguistic annotation with NLTK.ipynb | |2023/10/13| Lesson canceled due to UNIPI orientation days.| |2023/10/19| Feature Selection| 6 - Text Indexing 3 | L6.3 - Gensim collocations - Stanza - Spacy (Notebooks) | |2023/10/20| Vector space models | 6 - Text Indexing 4 | D. Jurafsky, J.H. Martin. Chp. 6. L6.4 - Vector space model - toy example| |2023/10/26| Lesson canceled| |2023/10/27| Lesson canceled| |2023/11/02| Machine Learning for Text Analytics. | 10 - Machine Learning for Text Analytics - corrected| |2023/11/03| Machine Learning for Text Analytics: Design Experimental Protocols. Student presentations: How to. | 11 - Design Experimental Protocols. 11.1 - Student presentations: How to | L.11 - Classification with SkLearn | |2023/11/09| Student project presentations: proposal, brainstorming, discussion. | |2023/11/10| Student project presentations: proposal, brainstorming, discussion. | |2023/11/16| Topic Modeling | 12 - Topic Modeling | Zhai and Massung (2016) Text Data Management and Analysis. Chp 17. L.12 -Topic Modeling - Notebook.. L.12.1 - Topic Modeling pyLDAvis - Notebook| |2023/11/17| A primer on Neural Networks |13 - A primer on Neural Networks | |2023/11/23|Neural Networks | 14 - Neural Networks | From SVM to NN, Classification with Keras - Notebooks. | |2023/11/24| Neural Language Models | 15 - Neural Language Models| D. Jurafsky, J.H. Martin. Chps. 7 9 11 | |2023/11/30| Student project presentations: ongoing experiments. Neural Language Models Practice | 16 - Neural Language Models Word2Vec| Word2vec - Notebook.| |2023/12/01| Student project presentations: ongoing experiments. Neural Language Models Practice | 17 - Neural Language Models Doc2Vec|Doc2Vec - Notebook| |2023/12/07| Neural Language Models - part 2 |Neural Language Models - part 2| |2023/12/11| BERT. Project Submission | 19 - Bert| ==== Exam ==== Attending students The exam for attending students will consist of the development of a project to be agreed upon with the teacher and an oral exam. The outcome of the project will be some code and a report of the activity (4-10 pages is the typical length range). The oral exam will consist of the presentation and discussion of the project. Projects may be based on challenges proposed in either research forums (Semeval, Evalita) or other platforms (Kaggle). Students are also invited to propose a project based on other sources (e.g., recent papers on ArXiv CL or AI), or their own interests. Students may work in 3-5 people groups. Non-Attending students The exam for non attending students will consist in a written exam with open question and exercises, and an oral discussion on the topics of the course. Written test example. ==== Textbooks ==== It is recommended to read selected chapters from: - D. Jurafsky, J.H. Martin, Speech and Language Processing. 3nd edition, Prentice-Hall, 2018. - S. Bird, E. Klein, E. Loper. Natural Language Processing with Python. Further bibliography will be indicated as a material for the single lessons. ==== Previous editions ==== * 2022-2023 * 2021-2022 * 2020-2021 * 2019-2020 * 2018-2019 * 2017-2018