lgirrbach Goto Github PK

aml-ss-21----bayesflow-on-long-term-data

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.

decision-trees-vs.-neural-networks

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

flr-project

hard-attention-transducer

End-to-end trainable autoregressive and non-autoregressive transducers using hard attention

hided

joeynmt-qrnn

lgirrbach.github.io

mammoth

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

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-glossing

Code for our SIGMORPHON 2023 shared task description paper: Tü-CL at SIGMORPHON 2023: Straight-Through Gradient Estimation for Hard Attention

sigmorphon-2023-inflection

Code for our SIGMORPHON 2023 shared task description paper: Tü-CL at SIGMORPHON 2023: Straight-Through Gradient Estimation for Hard Attention

tuereuth-legal-at-semeval-task-6

TüReuth Legal Code for SemEval 2023 Task 6: LegalAI.