This reporsitoy keeps an ongoing e-book about Natural Language Processing wiih Python with a focus on Portuguese Language (mainly Portugal and Brazil varieties) .
The main goal for this e-book is to show how to use python and the several libraries available to process the Portuguese language.
- Why Python?
- Python 2 vs Python 3
- Encodings
- Best Practices
- Lexicons
- Setiment Analysis
- OpLexicon
- LIWC
- SentiLex
- Priberam Subjective Lexicon
- Setiment Analysis
- Gazetters
- DBPedia
- Other lists
- Dicionaries
- Unitex
- Open Dictionary
- Wiki Dictionary
- Thesauri
- TEP
- Open Thesaurus
- Onto.PT
- Wordnets
- WordNet.BR
- WordNet.PT
- Onto.PT
- Open WordNet-PT
- MultiWordNet
- Corpora
- PoS
- MacMorpho
- Parsing
- Floresta Sinta(c)tica
- Sentiment Analysis
- Priberam Fine-Grained Opinion Corpus
- ReLi
- PoS
- Frequency Distribution
- Lexical Variety
- Zipf's law
- Luhn cut
- String distance
- Fuzzy matching
- Speech Recognition
- Language Detection
- Sentence Tokenization
- Word Tokenization
- Morphological Analysis
- Part of Speech Tagging
- Parsing
- Named Entity Recognition
- Semantic Analysis
- Speller
- Grammar checker
- Term Extraction
- Text Classification
- Topic Detection
- Automatic Summarization
- Word-sense -Disambiguation
- Machine Tranlation
- Sentiment Analysis
- Random-text Generation
- Bag-of-words
- Language Model
- Word Embeddings
- SVM
- CRF
- Random-forest
- chardet, unidecode
- PyEnchant, hunspell
- stemming
- Soundex, Metaphone
- Fuzzywuzzy, jellyfish
- brasil.vocab, certografia
- Whoosh, cwb-python, Pattern, Newspaper
- NLTK, TextBlob, MontyLingua, spaCy, PyNLPl, polyglot, PyPLN
- nlpnet, MBSP
- gensim
- sumy, textteaser, TextRank
- MITIE, RAKE
- scikit-learn, CRFsuite
Pedro Paulo Balage pedrobalage.com