dainis-boumber

AA_CNN

Multi-label CNN for Authorship Attribution

amamda

Adversarial Multi-Author Multi-Domain Adaptation

av

authorship verification

complexity

Complexity estimation project

domain-adaptation-kit

This library offers a unified approach to run a number of popular Domain Adaptation methods. It has some Deep Learning, but it is also meant to address the issue with most non-Deep Learning DA being done in Matlab.

nd_boundary_plot

A way to plot high-dimensional decision boundaries via Voronoi tesselation onto 2D

self-adaptive-learning

Selft adaptive learning technique for local classifiers

sentence-transformers

Sentence Embeddings with BERT & XLNet

tf-dann-py3

Domain Adversarial Neural Network for use in baslines against non-image ML datasets.

dainis-boumber/sentence-transformers

Sentence Embeddings with BERT & XLNet

dainis-boumber/hedwig

PyTorch deep learning models for document classification

dainis-boumber/MLP-400-datasets

Containers various NLP datasets made from 400 papers by top 20 authors by citation in Machine Learning

dainis-boumber/adaptation-metrics

Adapt Transformer-based language models to new text domains based on Ruder's 2017 paper

dainis-boumber/adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

dainis-boumber/bert-as-service

Mapping a variable-length sentence to a fixed-length vector using BERT model

dainis-boumber/dainis-boumber

dainis-boumber/dainis-boumber.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

dainis-boumber/deepsegment

A sentence segmenter that actually works!

dainis-boumber/domain_adaptability

Measure the adaptability of domains/datasets

dainis-boumber/fastai_dev

dev notebooks (for docs see http://docs.fast.ai and https://github.com/fastai/fastai)

dainis-boumber/Hub

🔌 A central repository collecting pre-trained adapter modules

dainis-boumber/ivy

The Unified Machine Learning Framework

dainis-boumber/LEAN-LIFE

Label Efficient Learning From Explanations

dainis-boumber/LongLoRA

Code and documents of LongLoRA and LongAlpaca

dainis-boumber/nerc-tools

dainis-boumber/nertools

A collection of custom NER tools that make tagging, labeling with custom labels, training a custom NER (NERC) model, evaluating it, and visualizing the results a lot easier by automating much of the process. Annotation to BIO/CoNLL-2003 file format, SpaCy, and SimpleTransformers dataframe is provided. Any library can be used for training from then on, but Flair, Spacy, SimpleTransformers are provided as along with evaluation and visualization.

dainis-boumber/nlp-loss-functions

Here I collect various loss functions, metrics, coefficients, and other things of similar nature that are not common and useful for NLP tasks I work on.

dainis-boumber/nn-template

Generic template to bootstrap your PyTorch project with PyTorch Lightning, Hydra, W&B, DVC, and Streamlit.

dainis-boumber/Practical_NLP_in_PyTorch

A repository containing tutorials for practical NLP using PyTorch

dainis-boumber/pytorch-functional

Provides functional API similar to the one from tensorflow.keras described at https://www.tensorflow.org/guide/keras/functional

dainis-boumber/quinine

A library to create and manage configuration files, especially for machine learning projects.

dainis-boumber/receipt-field-extractor

dainis-boumber/SATQR_bLM

SATQR_bLM is a design inspired by (and largely based on) SiATL; Chronopoulou et al. in proc., NAACL 2019

dainis-boumber/ssl_text_classification

Semi Supervised Learning for Text-Classification

dainis-boumber/tner

Language model fine-tuning on NER with an easy interface and cross-domain evaluation.

dainis-boumber/transformer-from-scratch-python

Transformer from scratch - python/pytorch version to serve as a crutch in learning a few new languages

dainis-boumber/Vue-Mazer-Dashboard

This is Mazer Dashboard in Vue

dainis-boumber/x-tagger

A Natural Language Processing toolkit for sequence labeling in its simplest form.

dainis-boumber/YouTokenToMe

Unsupervised text tokenizer focused on computational efficiency