alvations/awesome-community-curated-nlp

Community Curated NLP List

Awesome Community-Curated NLP List

To contribute: This list is community curated, anyone can do a pull-request to add to the list. And it will be merged once 5 person have verified that the PR is not spam.

Speech NLP

• Automatic Speech Recognition (Speech-to-Text)

  • Kaldi
  • CMU Sphinx
  • Julius
  • RWTH ASR

• Speech Synthesis (Text-to-Speech)

  • Merlin
  • Festival
  • HTS
  • eSpeak
  • Covarep
  • Free TTS
  • Ekho

• Generic Speech Analysis/Modelling Tools

  • Hidden Markov Model Toolkit
  • Praat

• List of Lists of Speech tools

  • https://en.wikipedia.org/wiki/Comparison_of_speech_synthesizers
  • https://en.wikipedia.org/wiki/List_of_speech_recognition_software

Text NLP Suites

• NLTK
• Gensim
• SpaCy
• Stanford CoreNLP
• Freeling
• OpenNLP
• DKPro
• PyNLPl
• IXA Pipes
• NLP4J
• CogComp's NLP libraries
• Stanbol NLP
• LIMA
• Corpus.Tools
• NooJ
• SALAT

Language Specific Text NLP Suites

• Arabic

  • SAFAR: Software Architecture For Arabic language pRocessing

• Cantonese

  • PyCantonese: Cantonese Linguistics and NLP in Python

• Chinese

  • SnowNLP: Simplified Chinese Text Processing

• Persian

  • Hazm: Python library for digesting Persian text.

• Dutch

  • Frog: An advanced NLP suite for Dutch

• Italian

  • Tint: Lend color to your Italian texts!

• Korean

  • KoNLPy: Korean NLP in Python

Pre-processing (Tokenization / Stemming / POS Tagging / etc.)

• Ngrams

  • Colibri Core - C++ and Python tools for n-grams and skipgrams

• Stemming

  • Snowball Stemmers
  • SerbianStemmer
  • Whoosh Stemmers

• Tokenizers

  • Elephant: Sequence labeling for word and sentence segmentation
  • Toktok: A fast, simple, multilingual tokenizer
  • Ucto: An advanced rule-based unicode-aware tokenizer

Deep Linguistic Processing

The deep here isn't "deep learing" deep ;P , see https://en.wikipedia.org/wiki/Deep_linguistic_processing

• Head-drive Phrase Structure Grammar (HPSG)

  • DELPH-IN: Deep Linguistic Processing with HPSG
  • English Resource Grammar

• Combinatory Categorial Grammar (CCG)

  • CCG2PST : A tool for converting CCG derivations into PTB-style phrase structure trees

Word Embeddings

• Word2Vec
• GloVe
• COMPOSE
• Polyglot
• FastText

Twitter

• PyTweet
• Twitter4J
• Affective Tweets

Task Specific

• Entity Linking / Relation Extraction

  • KNEWS: Knowledge Extraction With Semantics
  • Deep Dive: Relation Extraction

• Coreference

  • Berkley Coreference Error Analyser - A tool for classifying errors in coreference resolution

• Parsing

  • Berkley Parse Error Analyser: A tool for classifying mistakes in the output of parsers

Machine Translation

• Neural MT

  • OpenNMT
  • Amunmt
  • Google Seq2Seq
  • Eske Seq2seq

• Phrased-based MT

  • Moses MT
  • Joshua
  • Jane
  • Phrasal
  • Kriya

• Rule-based MT

  • Apertium MT

• Example-based MT

  • Kyoto EBMT

• MT-related tools

• MT List of lists

  • Friends of Moses
  • Let’s MT
  • Neural Machine Translation Implementations
  • @jonsafari A list of Neural MT implementations

Language Modelling

• SRILM
• IRSTLM
• KenLM
• NPLM
• Mikolov's RNNLM
• Yandex Fast-RNNLM

Annotation Related

• Annotation Platforms

  • Brat Rapid Annotation Tool: Online environment for collaborative text annotation
  • PyBossa: The ultimate crowdsourcing framework
  • FLAT: FoLiA Linguistic Annotation Tool

• Annotation Toools

  • TableAnnotator and TabInOut
  • Marvin: Semantic text annotation tools using Wordnet and DBPedia

Others

• Author Attribution

  • Java Graphical Authorship Attribution Program

• Orthography

  • Gecco: Generic Environment for Context-Aware Correction of Orthography
  • Charguana: Character Vomitting for CJK Unicode

• NLP API / Workflow

  • CLAM: Turn command-line applications into RESTful webservices with web front-end.
  • LuigiNLP: Experimental NLP Pipeline system built on top of SciLuigi
  • TextFlows / ClowdFlows

• Misc

  • Vinci generative environment

NLP Related Machine Learning Tools

• Timbl - Memory-based machine learning
• KeLP: Kernel-based Learning Platform

List of Lists of NLP Resources/Tools

• Awesome NLP (The original one, curated by @keon and @outpark)
• Repo tagged with nlp on Github.com
• Java or Python for NLP?
• OpenSource Deep QA Resources (also nice talk)
• Sibawayh Repository for Arabic NLP
• @proycon La Machine
• Ruby NLP Resources/Tools

Dataset Lists

• @niderhoff NLP Datasets
• @karthikncode NLP Datasets

See Also

• Corpora List: Your source of all thing computational linguistics / NLP / corpora
• LT World: Language Technology World
• META Net
• LDC: Linguistic Data Consortium
• OLAC: Open Language Archives Community
• NLSR: Natural Language Software Registry