aikho

awesome-feature-engineering

A curated list of resources dedicated to Feature Engineering Techniques for Machine Learning

aikho.github.io

Blog about machine learning and AI-powered systems (not English)

2018DSB

2018 Data Science Bowl 2nd Place Solution

awesome-relation-extraction

📖 A curated list of awesome resources dedicated to Relation Extraction, one of the most important tasks in Natural Language Processing (NLP).

awesome-transfer-learning

Best transfer learning and domain adaptation resources (papers, tutorials, datasets, etc.)

awsome-domain-adaptation

A collection of AWESOME things about domian adaptation

bdm-tool

ConvBert

data_science_bowl_2018

My 5th place (out of 816 teams) solution to The 2018 Data Science Bowl organized by Booz Allen Hamilton

docker-python

Kaggle Python docker image

dsb2018_topcoders

DSB2018 [ods.ai] topcoders

DSB_2018

eda_nlp

Easy data augmentation techniques for boosting performance on text classification tasks.

FlowQA

Implementation of conversational QA model: FlowQA (with slight improvement)

hybif

ir_datasets

Provides a common interface to many IR ranking datasets.

Kaggle-Carvana-3rd-Place-Solution

3rd place solution ( Carvana Image Masking Challenge )

kaggle_2018_data_science_bowl_solution

4th place solution for 2018 Data Science Bowl kaggle competition

Kaggle_TGS2018_4th_solution

Kaggle TGS Salt Identification Challenge 2018 4th place code

Keras-RetinaNet-for-Open-Images-Challenge-2018

Code for 15th place in Kaggle Google AI Open Images - Object Detection Track

MHGRN

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (EMNLP 2020)

minecraft-dialogue-models

multihead_joint_entity_relation_extraction

Implementation of our papers Joint entity recognition and relation extraction as a multi-head selection problem (Expert Syst. Appl, 2018) and Adversarial training for multi-context joint entity and relation extraction (EMNLP, 2018).

nlpaug

Data augmentation for NLP

PLMpapers

Must-read Papers on pre-trained language models.

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

pytorch-saltnet

Kaggle | 9th place single model solution for TGS Salt Identification Challenge

tag-based-multi-span-extraction

The official implementation of EMNLP 2020, "A Simple and Effective Model for Answering Multi-span Questions".

TextAttack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP

transformers

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