Pinned Repositories
A-Guide-to-Deep-Learning
π A detailed guide to deep learning: http://yerevann.com/a-guide-to-deep-learning/
BARTSmiles
BARTSmiles, generative masked language model for molecular representations
BioRelEx
𧬠BioRelEx: Biological Relation Extraction Benchmark @ ACL BioNLP Workshop 2019
ChemLactica
Fine-tuning Galactica and Gemma to operate on SMILES. Integrates into a molecular optimization algorithm.
Dynamic-memory-networks-in-Theano
Implementation of Dynamic memory networks by Kumar et al. http://arxiv.org/abs/1506.07285
mimic3-benchmarks
Python suite to construct benchmark machine learning datasets from the MIMIC-III π clinical database.
PARASITE
πͺ± PARASITE || A parallel sentence data preprocessing toolkit. Originally developed as a part of the `en-ru` winner submission of WMT20 Biomedical Translation Task.
R-NET-in-Keras
Open R-NET (hy` Υ‘ΥΌΥΆΥ₯ΥΏ π) implementation and detailed analysis: https://git.io/vd8dx
Spoken-language-identification
Spoken language identification with deep learning
WARP
Code for ACL'2021 paper WARP π Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification. https://aclanthology.org/2021.acl-long.381/
YerevaNN's Repositories
YerevaNN/mimic3-benchmarks
Python suite to construct benchmark machine learning datasets from the MIMIC-III π clinical database.
YerevaNN/A-Guide-to-Deep-Learning
π A detailed guide to deep learning: http://yerevann.com/a-guide-to-deep-learning/
YerevaNN/WARP
Code for ACL'2021 paper WARP π Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification. https://aclanthology.org/2021.acl-long.381/
YerevaNN/BARTSmiles
BARTSmiles, generative masked language model for molecular representations
YerevaNN/BioRelEx
𧬠BioRelEx: Biological Relation Extraction Benchmark @ ACL BioNLP Workshop 2019
YerevaNN/ChemLactica
Fine-tuning Galactica and Gemma to operate on SMILES. Integrates into a molecular optimization algorithm.
YerevaNN/SciERC
A fork of https://bitbucket.org/luanyi/scierc/src
YerevaNN/PARASITE
πͺ± PARASITE || A parallel sentence data preprocessing toolkit. Originally developed as a part of the `en-ru` winner submission of WMT20 Biomedical Translation Task.
YerevaNN/Relation-extraction-pipeline
Pipelines that combine different modules to perform relation extraction
YerevaNN/SSL-playground
YerevaNN/zsee
Zero Shot Event Extraction - Making pretrained sentence encoders more multilingual and language-agnostic. Works best (at the moment) with YerevaNN's internal version of allennlp.
YerevaNN/Molecular_Generation_with_GDB13
YerevaNN/NLOS-Localization-WAIR-D
YerevaNN/YNNtitan
A YerevaNNative PyTorch Library for large model training
YerevaNN/allennlp
YerevaNN's internal branches for AllenNLP - An open-source NLP research library, built on PyTorch.
YerevaNN/dom-gen-failure-modes
YerevaNN/metaseq
Repo for external large-scale work
YerevaNN/yarx
YARX - Yet Another Relation eXtraction framework, based on SciIE architecture and AllenNLP framework
YerevaNN/BIG-bench
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
YerevaNN/biorelex-codalab-submission
Sample baseline submission for BioRelEx codalab competition.
YerevaNN/ChemLacticaTestSuite
YerevaNN/datasets
π€ The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools
YerevaNN/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
YerevaNN/GLIP
Grounded Language-Image Pre-training
YerevaNN/mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
YerevaNN/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
YerevaNN/relex-webapp
YerevaNN/scispacy
A full spaCy pipeline and models for scientific/biomedical documents.
YerevaNN/spaCy
π« Industrial-strength Natural Language Processing (NLP) with Python and Cython
YerevaNN/transformers
π€ Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.