Awesome NLP Projects

This is a curated list of Natural Language Processing (NLP) projects that make a geek smile for they exist.

This list are directly connected or may be used for Natural Language Processing. Inspited by Joseph Misiti's github project

Contents

• Resources and Frameworks
• Related Lists
• Deep Learning goodies
• Machine Learning
• Language modelling
• Other ML
• Other Cool stuff
• Contribute
• License

Resources and Frameworks

• TRIPS . Semantic Lexicon link . semantic parser link . [link] (http://trips.ihmc.us/parser/cgi/parse)
• C&C Boxer . semantic parser link
• EPILOG . episodic logic framework link
• KNEXT (the continuation of the Lore project) . knowledge extraction into episodic logic (similar to babelnet) link
• FRED . semantic parser/knowledge extractor link
• DELPH-IN . Broader project for NLP; grammar, parser, link
• LKB . The LKB system is a grammar and lexicon development environment for use with unification-based linguistic formalisms. link
• Malt parser . dependecy syntax parser link
• YAGO . knowledge base link
• GATE . text engineering pipeline link
• Enju . syntactic parser link
• Open NLP . NLP framework in Java link
• CoreNLP . stanford core NLP framework for parsing link
• NLTK . awersome NLP framework in Python link
• Valex . Categorization of English Verbs link
• Unified verb Index . VerbNet and FrameNEt togetehr link
• scikit-learn . Machine learning in Python. Simple and efficient tools for data mining and data analysis link
• Tuffy . Scalable Markov Logic inference engine link
• Fexlix . the successor of Tuffy link
• Alchemy . algorithms for statistical relational learning and probabilistic logic inference, based on the Markov logic representation link
• pracmln . Marcov Logic in Python, this project started as a fork to ProbCong project. Find more link
• ProbCog . ProbCog is a statistical relational learning and reasoning system that supports efficient learning and inference in relational domains link
• KReator . KReator is an integrated development environment (IDE) for relational probabilistic knowledge representation languages. At the moment, KReator supports Bayesian Logic Programs (BLPs), Markov Logic Networks (MLNs), Relational Maximum Entropy (RME), Relational Bayesian Networks (RBN), and Probabilistic Prolog (ProbLog). link
• pyHTM . pyHTM - Hierarchical Temporal Memory in Python; . Our machine intelligence technology is called Hierarchical Temporal Memory (HTM), which is a detailed computational theory of the neocortex. At the core of HTM are time-based learning algorithms that store and recall spatial and temporal patterns. HTM is well suited to a wide variety of problems, particularly those with the following characteristics: . Streaming data rather than static databases . Underlying patterns in the data change over time . Many individual data sources where hand crafting separate models is impractical . Subtle patterns that can’t always be seen by humans . Time-based patterns . Simple techniques such as thresholds yield substantial false positives and false negatives . [link] (https://github.com/carver/pyHTM)
• KnowRob . KnowRob is a knowledge processing system that combines knowledge representation and reasoning methods with techniques for acquiring knowledge and for grounding the knowledge in a physical system and can serve as a common semantic framework for integrating information from different sources. KnowRob combines static encyclopedic knowledge, common-sense knowledge, task descriptions, environment models, object information and information about observed actions that has been acquired from various sources (manually axiomatized, derived from observations, or imported from the web). It supports different deterministic and probabilistic reasoning mechanisms, clustering, classification and segmentation methods, and includes query interfaces as well as visualization tools. link
• GHMM . The General Hidden Markov Model library (GHMM) is a freely available C library implementing efficient data structures and algorithms for basic and extended HMMs with discrete and continous emissions. It comes with Python wrappers which provide a much nicer interface and added functionality. link . pyHSMM "This is a Python library for approximate unsupervised inference in Bayesian Hidden Markov Models (HMMs) and explicit-duration Hidden semi-Markov Models (HSMMs), focusing on the Bayesian Nonparametric extensions, the HDP-HMM and HDP-HSMM, mostly with weak-limit approximations. There are also some extensions: . autoregressive models . switching linear dynamical systems . factorial models . link
• Prism . symbolic-statistical models; a model checker for temporal logic and quantitative extensions; verification for realtime systems; markov models etc. . link
• UBY . A Large-Scale Unified Lexical-Semantic Resource link
• Duckling . probabilistic CFG parser for dimensions (time, temperature, size etc) link
• Wit . intent parser link
• Mycroft . a company making another intent parser, a Speech2Text and a Text2Speech frameworks in Python link
• IEPY . IEPY is an open source tool for Information Extraction focused on Relation Extraction.link
• MITIE . This project provides free (even for commercial use) state-of-the-art information extraction tools. The current release includes tools for performing named entity extraction and binary relation detection as well as tools for training custom extractors and relation detectors. link
• SyntaxNet . an open-source neural network framework for TensorFlow that provides a foundation for Natural Language Understanding (NLU) systems. Our release includes all the code needed to train new SyntaxNet models on your own data, as well as Parsey McParseface, an English parser that we have trained for you, and that you can use to analyze English text. link
• OpenAI Gym . A toolkit for developing and comparing reinforcement learning algorithms. link
• spiff workflow . Spiff Workflow is a library implementing a framework for workflows. It is based on http://www.workflowpatterns.com and implemented in pure Python. link [Workflow patterns] (http://www.workflowpatterns.com/) The aim of this initiative is to provide a conceptual basis for process technology. In particular, the research provides a thorough examination of the various perspectives (control flow, data, resource, and exception handling) that need to be supported by a workflow language or a business process modelling language.
• A news reader project . link

Deep Learning goodies

• Neural Storry teller code

Language modelling

• Skip Sentence encoder code, paper
• Attentive reader code, paper

Other ML

• deep learning platform MxNet + NuymPy code

Other Cool stuff

• Node Box . NodeBox makes it easy to do data visualisations, generative design and complex production challenges. link
• Callimacus - Linked open data, RDF, web application, data visualization etc. link
• Feature Forge . This library provides a set of tools that can be useful in many machine learning applications (classification, clustering, regression, etc.), and particularly helpful if you use scikit-learn (although this can work if you have a different algorithm). [link][https://github.com/machinalis/featureforge/tree/master]
• Storry generator algorithms . [link][http://wikis.sub.uni-hamburg.de/lhn/index.php/Story_Generator_Algorithms]
• OpenCog AI framework OpenCog is an open-source software project aimed at directly confronting the Artificial General Intelligence (AGI) challenge, using mathematical and biological inspiration and professional software engineering techniques. . link

Similar lists

• Rochester University project list . potentially useful links . link
• Misiti's list . link
• Description Logic reasoners . list of reasoners link
• Illinois Projects List . of software from Illinois Cognitive Computation Group link

Contribute

Contributions welcome! Read the contribution guidelines first.

License

To the extent possible under law, Eugeniu Costezki has waived all copyright and related or neighboring rights to this work.