Site
Research
Links
- Cartaz digital - Biblioteca do ISCTE
- ISCApad Archive
- ISCA online archive
- http://techtalks.tv/events/76/ - Videos of the 1st Lisbon Machine Learning School (LxMLS 2011)
- http://pesquisa.biblioteca.iscte.pt/ - ISCTE-IUL Library portal
Seminars
Tutorials and References
- Jay Alammar Blog. - Visualizing machine learning one concept at a time (RNNs, attention, transformers, Bert, etc. Nice illustrations
- The Illustrated Transformer - Jay Alammar, Visualizing machine learning one concept at a time (série de tutoriais muito interessantes)
- Visualizing machine learning one concept at a time (Sugestão da Luisa)
- Book: Dive into Deep Learning
- http://www.superlectures.com/sigdial2012/, IEEE-IST Academic - SigDial Conference in 2012 talks
- Natural Language Processing by Chris Manning and Dan Jurafsky
- Github page of Jacob Eisenstein, NLP Book,
- Repository containing a number of different models implemented in TensorFlow
- DIY Deep Learning for Vision: a Hands-On Tutorial with
- http://www.html5rocks.com/en/tutorials/webaudio/intro/ HTML 5 - GETTING STARTED WITH WEB AUDIO API
- Machine Translation using Moses: Tutorial, Factored training, Manual
- Statistical Machine Translation Book by Philipp Koehn
- iVector Tutorial - Interspeech 2011
- Exploring the Limits of Language Modeling - (11 Feb 2016) "Our best single model significantly improves state-of-the-art perplexity from 51.3 down to 30.0 (whilst reducing the number of parameters by a factor of 20), while an ensemble of models sets a new record by improving perplexity from 41.0 down to 24.2. We also release these models for the NLP and ML community to study and improve upon."
- Probabilistic and Statistical Modeling in Computer Science - Free Book.
- Topic Modelling: LDA with Python and LDA with Python. What is a good explanation of LDA
- Convolutional neural network with The Simpsons - recognizing Simpson characters - walkthrough
- Open Source Tools & Data for Music Source Separation - Music Source Separation tutorial (ISMIR 2020)
- How to Build a Simple Machine Learning Web App in Python
Online tools
- Online Annotator agreement -Calculates Reliability for 3+ Coders
- CitiusTagger and CitiusNec - A PoS-Tagger and Named Entity Classification tool for Portuguese and Spanish
- Microsoft Face plus - Face detection and classification
- Sentilecto - Entity-based Sentiment Analysis in Spanish and Portuguese
- Festival Text-to-Speech Online Demo - Examples and Demos of HTS and Unit Selection speech synthesisers
- http://www.linguee.com - translation tool combining an editorial dictionary and a search engine
- http://www.co.it.pt/~labfala/g2p/ - Conversor de Grafemas para Fonemas (Português)
- http://connective-lex.info - database of connective lexicons in various languages
Toolkits and libraries
- SetFit: Efficient Few-Shot Learning Without Prompts
- http://crfpp.googlecode.com/svn/trunk/doc/index.html - CRF++: Yet Another CRF toolkit
- http://www.chokkan.org/software/crfsuite/ - A fast implementation of Conditional Random Fields (CRFs)
- http://www.chokkan.org/software/liblbfgs/ - libLBFGS: a library of Limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS)
- http://www.chokkan.org/software/classias/ - Collection of machine learning tools
- Apache OpenNLP library - machine learning based toolkit for the processing of natural language text (models).
- library for industrial-strength natural language processing - in Python and Cython
- http://wami.csail.mit.edu/sandbox.php Testing Speech recognition - write-and-try SR grammars
- http://nlp.lsi.upc.edu/freeling - FreeLing - An open-source suite of Language Analysers. Online demo (works for Portuguese)
- FaNT - Filtering and Noise Adding Tool
- Data visualisation tools and book - An overview
- Concept Net 5
- Babelnet - very large multilingual encyclopedic dictionary and semantic network
- LIWC - Linguistic Inquiry and Word Count
- SentiWordNet - (CC Licence) assigns to each synset of WordNet three sentiment scores: positivity, negativity, objectivity
- OpeNER Project - Several web services and software tools: NER tagger, NER, NED, Coreference, Constituency parsers, Opinion taggers, Sentiment Polarity taggers, Language detectors, tokenizers, part-of-speech taggers and lemmatizers for 6 languages (English, Spanish, French, Italian, Dutch and German)
- Stanford Software for NLP
- http://mloss.org/software/ - Machine Learning Open-source software
- http://www.accurat-project.eu - ACCURAT Toolkit - a collection of tools for comparable corpora collection and multi-level alignment and information extraction from comparable corpora
Data
- Coswara - A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis - https://github.com/iiscleap/Coswara-Data (corpus still under collection, open access at https://github.com/iiscleap/Coswara-Data)
- Google AudioSet - A massive dataset of, manually annotated audio events
- http://nats.gitlab.io/swc/ Spoken Wikipedia Corpora (About)
- Coco dataset