The Artificial Language Toolkit: this is a Python library (in very active development) to facilitate research using artificial languages, especially in semantic typology. Current tools focus on efficient communication and grammars for expressions in a language-of-thought.
+ULTK: The Unnatural Language Toolkit: this is a Python library (in very active development) to facilitate research using unnatural languages, especially in semantic typology. Current tools focus on efficient communication and grammars for expressions in a language-of-thought.
lm-training: a skeleton for config-driven training of language models on your own data, using HuggingFace. Includes the ability to use HF's Trainer to train recurrent models in addition to transformers.
The Modal Typology Database: a database recording observations about the semantic typology of modals in natural language, focusing on the force-flavor pairs that they can express. This is a growing resource, designed to be easy to contribute to, so please consider so doing!
edugrad: a minimal re-implementation of the PyTorch API for building dynamic computation graphs and computing gradients via backpropagation, designed for pedagogical purposes.