Python and NLTK

• Python: https://www.python.org/downloads/ Use 3.[something]
• NLTK: Installing NLTK itself: http://www.nltk.org/install.html You also need the NLTK data, see http://www.nltk.org/data.html

Learning Python:

• How To Think Like A Computer Scientist is a very good and accessible online Python textbook
• A Python tutorial

 Tutorials and texts about distributional models

• Count-based models:
• Turney and Pantel overview article
  
  
• Neural network based, deep learning models:
  
• Book by Goodfellow, Bengio and Courville (text available online)
• 2013 deep learning tutorial by Socher, Manning and Bengio
  

• Latent Dirichlet Allocation (LDA) topic models:

• Mark Steyvers & Thomas Griffiths (2007), Probabilistic topic models
• Kevin Knight (2009), Bayesian Inference with Tears
• Alexander Koller, LDA with pirates and ninjas, and non-parametric Bayesian models with pirates and ninjas
  

Toolkits for computing distributional models

• Word2Vec
• GloVE
  
• dv: computing distributional models in which the dimensions are dependency parse snippets
  
• the DISSECT toolkit for computing distributional models and for doing compositional distributional semantics
• S-space
• gensim

Pre-computed spaces

• Word2Vec
• GloVE
• TypeDM
  

Logic-based semantics in the Natural Language Toolkit

While the Blackburn and Bos book uses Prolog, we will use the (Python-based) Natural Language Toolkit.

• The Natural Language Toolkit (NLTK)
  
• NLTK book chapter: Analyzing semantics in the Natural Language Toolkit
• A paper by the authors of the semantics part of NLTK: Dan Garrette and Ewan Klein (2009), An Extensible Toolkit for Computational Semantics. Proceedings of IWCS. 
• NLTK howto: Semantics
• Discourse representation (DRT) in NLTK: a paper, and the package
  
• NLTK API
  

Data

Data that can be used to build distributional models:

• The WaCKy corpora, including UKWaC (English web text, 2B words), Wackypedia (an English Wikipedia dump, 2B words), web corpora for French, German, and Italian. Ask me about a parsed version of UKWaC and Wackypedia if you need syntactic analysis.
  
• Catalan/Spanish/English wikicorpus

Deep semantic annotation:

• The Groningen Meaning Bank
  

Systems and online demos for logic-based semantic analysis

• The new Boxer demo is at http://www.let.rug.nl/bjerva/gmb/webdemo/demo.php.  Warning: frequently down.
  
• Boxer: syntactic and semantic analysis, system downloadable. For a demo, scroll to the bottom to generate DRSs for arbitrary English sentences
• LinGO English Resource Grammar: demo that generates Minimal Recursion Semantics representations
• Theorem proving (automatic inference):  Prover9 and Mace4

Prolog resources

• SWI Prolog
• Online book: Learn Prolog now!
  

Books about logic-based computational semantics

Taking more of a practical perspective:

• Blackburn and Bos: Representation and Inference for Natural Language,
   table of contents here
  
• van Eijck and Unger: Computational Semantics with Functional Programming

Focusing on the theory:

• L.T.F Gamut: Logic, Language, and Meaning (2 volumes)