yipingnus Goto Github PK

bayesian-error-estimation

contextual-eval-dataset

Evaluation Dataset for "Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia" (TextGraphs-15 Workshop@NAACL 2021)

criticalai

defminer

Mining Scientific Terms and their Definitions: A Study of the ACL Anthology (EMNLP 2013). [code+data]

dissertation

[M.S. Dissertation] Lightly-Supervised Learning Methods for One-Class Text Classification

docker

dont-stop-pretraining

Implementing of the paper "Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks" (ACL 2020) in Huggingface library.

fastai-playground

Experiments using Fastai and Pytorch library. Learning the core concepts and having some fun at the mean time.

figure8-contextual-dataset

fortify

Learning notes for https://www.joinfortify.com/

fuzzywuzzy

Fuzzy String Matching in Python

gensim

Topic Modelling for Humans

gpt-hate-check

GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection? (LREC-COLING2024 code+data)

huggingface-learning-notes

Explore HuggingFace library and try out language generation with various transformers.

indaba-2018

Practical Notebooks for the Deep Learning Indaba 2018

jamr

jd-cmd

Command line Java Decompiler

lotclass

[EMNLP 2020] Text Classification Using Label Names Only: A Language Model Self-Training Approach

machine-learning-labs

Lab Questions for 2301793-2019 class at Chulalongkorn University (Special Topics in CS - Modern Machine Learning)

mltrain-nips-2017

This repository contains all the material for the MLTrain NIPS workshop

naacl-2021-fudge-controlled-generation

nle-supplementary-dataset

The evaluation datasets used in: Yiping Jin, Dittaya Wanvarie, Phu T. V. Le, Learning from Noisy Out-of-Domain Corpus Using Dataless Classification. Natural Language Engineering (2020)

nlptools

A toolkit that wraps various natural language processing implementations behind a common interface.

nn-python

The useful and used parts of NN-Dropout

nyt-dataset

ollie

Ollie is a open information extractor that uses bootstrapped dependency paths.

openie

Quality information extraction at web scale.

optimal-ctr-bidding

A training and testing framework supporting experiments in CIKM 2016 paper "User Response Learning for Directly Optimizing Campaign Performance in Display Advertising"

optimseed

OptimSeed - Seed Word Selection for Weakly-Supervised Text Classification [NAACL SRW 2021]

product-nets