Leander Girrbach's repositories
sigmorphon-2023-glossing
Code for our SIGMORPHON 2023 shared task description paper: Tü-CL at SIGMORPHON 2023: Straight-Through Gradient Estimation for Hard Attention
hard-attention-transducer
End-to-end trainable autoregressive and non-autoregressive transducers using hard attention
PyTorch-QRNN
Proof-of-concept implementation of QRNN Layer in Pytorch. Recurrent pooling is implemented purely in PyTorch, no Python loop and also no extra CUDA code.
Sequence-Labelling
LSTM model for sequence labelling. Includes option to expand input length by constant. Currently implements cross-entropy, crf, and ctc losses.
sigmorphon-2023-inflection
Code for our SIGMORPHON 2023 shared task description paper: Tü-CL at SIGMORPHON 2023: Straight-Through Gradient Estimation for Hard Attention
Cognate-Reflex-Prediction
Contains modification of hard transducers to predict cognate reflexes (SIGTYP 2022 shared task). The encoder is changed in order to process multiple-sequence-alignment grids of multiple cognates instead of single sequences.
Discrete-Latent-Representation
Implementation of a straight-through gradient wrapper to allow for discrete latent representations. Provides binary discretizer which maps hidden representations to {0, 1} and a learnable multi-value discretizer, which maps hidden activations to their closest value in a set of given size.
EM-G2P-Aligner
Python implementation of the many-to-many aligner proposed by Jiampojamarn et al. (2007): Applying Many-to-Many Alignments and Hidden Markov Models to Letter-to-Phoneme Conversion
mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning
Tuereuth-Legal-at-SemEval-Task-6
TüReuth Legal Code for SemEval 2023 Task 6: LegalAI.