elronbandel

alephbert

auto-contrastive-generation

Text generation using language models with multiple exit heads

clustering

We use 5 different clustering algorithms to learn meaningful clusters in 3 different datasets. The clustering algorithms we use, KMeans, GMM, Louvain, Prim and DBSCAN are all unsupervised learning algorithms that utilize different approaches to find meaningful clusters in the data. In this work we apply every one of them on each of the datasets, search for optimal hyper parameters and discuss the different results.

lexical-generalization

Lexical Generalization Improves with Larger Models and Longer Training (EMNLP 2022)

transformer-sequence-labeling

Using PyTorch Transformer for sequnce labeling

webpages-url-spider

crawler for scraping web pages urls from list of required websites domains

fastfit

FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes

quality-controlled-paraphrase-generation

Quality Controlled Paraphrase Generation (ACL 2022)

unitxt

🦄 Unitxt: a python library for getting data fired up and set for training and evaluation

AlephBERT-demo

Demo for AlephBERT: Language Model Pre-training and Evaluation from Sub-Word to Sentence Level (ACL 2022)

elronbandel/lexical-generalization

Lexical Generalization Improves with Larger Models and Longer Training (EMNLP 2022)

elronbandel/clustering

We use 5 different clustering algorithms to learn meaningful clusters in 3 different datasets. The clustering algorithms we use, KMeans, GMM, Louvain, Prim and DBSCAN are all unsupervised learning algorithms that utilize different approaches to find meaningful clusters in the data. In this work we apply every one of them on each of the datasets, search for optimal hyper parameters and discuss the different results.

elronbandel/transformer-sequence-labeling

Using PyTorch Transformer for sequnce labeling

elronbandel/alephbert

elronbandel/auto-contrastive-generation

Text generation using language models with multiple exit heads

elronbandel/char-base-hebrew-bert

Training Longformer with cross-word global attention and ConvBERT on Whole Word Masking with character level Hebrew input.

elronbandel/simple-lstm-crf

simple lstm crf implementation with POS example

elronbandel/datasets

🤗 Fast, efficient, open-access datasets and evaluation metrics in PyTorch, TensorFlow, NumPy and Pandas

elronbandel/ebook

elronbandel/elronbandel.github.io

elronbandel/expectation_maximzation

elronbandel/flow-based-compression

Flow Based Generative Models with Virtual Bottleneck Compression

elronbandel/label-sleuth

An open source no-code system for text annotation and building text classifiers

elronbandel/learning-regex-with-lstm

Exploring the capabilities of LSTM models with the task of Regular Language Deciding.

elronbandel/lingustic-generator

elronbandel/lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

elronbandel/low-resource-text-classification-framework

Research framework for low resource text classification that allows the user to experiment with classification models and active learning strategies on a large number of sentence classification datasets, and to simulate real-world scenarios. The framework is easily expandable to new classification models, active learning strategies and datasets.

elronbandel/nquad

Natural Question Dataset in SQuAD 2.0 format

elronbandel/rasabot

elronbandel/relation-extraction

experimental project

elronbandel/sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

elronbandel/sign-translate

elronbandel/simple-vae

Simple implementation of variational autoencoder (VAE)

elronbandel/sprybot

elronbandel/transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

elronbandel/trl

Train transformer language models with reinforcement learning.

elronbandel/unsupervised-learning

elronbandel/word-level-character-level-lstm

elronbandel/word2vec-without-deep-learning

Converting all words from wikipedia to Dense Vectors representation (using PMI Probabilities without any Deep Learning) and finding similarities based on the vector representation..

elronbandel/xor-problem-solved-with-mlp