abasirat

abasirat.github.io

boltzmann-machines

Boltzmann Machines in TensorFlow with examples

diffdp

Differentiable Perturb-and-Parse operator

LingInfo-in-WordEmbeddings

llm-adapter

A plug-and-play adapter architecture that efficiently adapts large language models to downstream tasks. Essential for client-server architecture language model services. A practical approach to adapting LLMs' hidden activations without modifying the base model.

principal_word_vectors

We use principal component analysis for word embedding. The method is able to process both annotated and raw corpora.

Shifted-Randomized-SVD

An extention of the randomized singular value decomposition (SVD) algorithm to estimate the SVD of a shifted data matrix without explicitly constructing the matrix in the memory. With no loss in the accuracy of the original algorithm, the extended algorithm provides for a more efficient way of matrix factorization. The algorithm facilitates the low-rank approximation and principal component analysis (PCA) of off-center data matrices. When applied to different types of data matrices, our experimental results confirm the advantages of the extensions made to the original algorithm.

ud-tagger

A multi-task neural network model for multi-tagging of natural languages

UDP

uuparser

A transition-based parser for Universal Dependencies with BiLSTM word and character representations.

abasirat/principal_word_vectors

We use principal component analysis for word embedding. The method is able to process both annotated and raw corpora.

abasirat/llm-adapter

A plug-and-play adapter architecture that efficiently adapts large language models to downstream tasks. Essential for client-server architecture language model services. A practical approach to adapting LLMs' hidden activations without modifying the base model.

abasirat/ud-tagger

A multi-task neural network model for multi-tagging of natural languages

abasirat/abasirat.github.io

abasirat/boltzmann-machines

Boltzmann Machines in TensorFlow with examples

abasirat/diffdp

Differentiable Perturb-and-Parse operator

abasirat/LingInfo-in-WordEmbeddings

abasirat/Shifted-Randomized-SVD

An extention of the randomized singular value decomposition (SVD) algorithm to estimate the SVD of a shifted data matrix without explicitly constructing the matrix in the memory. With no loss in the accuracy of the original algorithm, the extended algorithm provides for a more efficient way of matrix factorization. The algorithm facilitates the low-rank approximation and principal component analysis (PCA) of off-center data matrices. When applied to different types of data matrices, our experimental results confirm the advantages of the extensions made to the original algorithm.

abasirat/UDP

abasirat/uuparser

A transition-based parser for Universal Dependencies with BiLSTM word and character representations.