Code

The Universal Decompositional Semantics (UDS) dataset and the Decomp toolkit

Develop probabilistic semantic grammar fragments and convert them to Stan code.

Web-based tool for developing annotation ontologies for video data with automated video analysis, object detection, and intelligent ontology suggestions.

Decentralized eprints on ATProto

A Python framework for constructing, deploying, and analyzing large-scale linguistic judgment experiments with active learning.

Unified data models and interfaces for syntactic and semantic frame ontologies.

Tools for detecting the use of AI assistance in crowd-sourced data collection

A high-performance Rust library for weighted finite-state transducers with comprehensive semiring support.

Modular spectral transformer implementations in PyTorch with Fourier, wavelet, and other frequency-domain operations for efficient sequence modeling.

A flexible framework for text annotation built on a hardened data model.

Composable ATProto Lexicon schemas for representing, sharing, and interlinking linguistic annotation data across text, audio, video, and image modalities.

A universal schema migration engine built on Generalized Algebraic Theories with automatic lens generation and bidirectional data transformation across 77 schema languages.