geraldzakwan
Senior Data Scientist at Provenir AI. MS in CS at Columbia University. Works in Data Science, Machine Learning, and Natural Language Processing.
@columbiaJakarta, Indonesia
Pinned Repositories
adempiere
ADempiere Business Suite ERP/CRM/MFG/SCM/POS done the Bazaar way in an open and unabated fashion. Focus is on the Community that includes Subject Matter Specialists, Implementors and End-Users.
AnonymizationAPI
debugging_search_relevance
The repository is created as a supporting material for a seminar that I gave at Bukalapak. It functions as a "Mini" ElasticSearch that I use to demo some Search Engine basic functionalities: indexing, matching and ranking.
Final-Project-API-v1.1
instagram_comments_topic_classification
Topic Classification for Indonesian Social Media Comments
iykra-sentiment-analysis
The repository is dedicated to the hands-on session at IYKRA Data Fellowship Program Batch 5 (https://iykra.com/datafellowship/). As a trainer, I design a sentiment analysis module for the participants to work on (improving the latency of the model or implementing model update). The assignment can be accessed here: https://github.com/geraldzakwan/iykra-sentiment-analysis/tree/assignment.
nlp-fall-2019
This repository is for the COMS 4705 Natural Language Processing course assignments that I took at Columbia in Fall 2019. More on the course (this is with a different professor but the syllabus is similar): http://www.cs.columbia.edu/~mcollins/cs4705-spring2019/.
parallel-mt-inference
This repository is for the COMS 6998 Practical Deep Learning System Performance course final project that I took at Columbia (https://www.cs.columbia.edu/education/ms/fall-2020-topics-courses/#e6998010). In this project, my teammate and I investigate parallelism in NLP. We experimented on how parallelism (e.g. using multi-head attention instead of recurrent connection and splitting input for inference) affects model performance (accuracy and speed-wise). More on it here http://bit.ly/pract-dl-final-report.
soal-kerja
Kumpulan soal tes kerja
tajong.ai
"Hafalin" app repository, a web app that could automatically generate academic questions (multiple choice and short answer) given a document in Indonesian, e.g. elementary school history lesson. Submitted for a Hackathon competition held by Kata.ai. More on it in https://blog.kata.ai/en/post/katahack-2-0-2/.
geraldzakwan's Repositories
geraldzakwan/instagram_comments_topic_classification
Topic Classification for Indonesian Social Media Comments
geraldzakwan/iykra-sentiment-analysis
The repository is dedicated to the hands-on session at IYKRA Data Fellowship Program Batch 5 (https://iykra.com/datafellowship/). As a trainer, I design a sentiment analysis module for the participants to work on (improving the latency of the model or implementing model update). The assignment can be accessed here: https://github.com/geraldzakwan/iykra-sentiment-analysis/tree/assignment.
geraldzakwan/tajong.ai
"Hafalin" app repository, a web app that could automatically generate academic questions (multiple choice and short answer) given a document in Indonesian, e.g. elementary school history lesson. Submitted for a Hackathon competition held by Kata.ai. More on it in https://blog.kata.ai/en/post/katahack-2-0-2/.
geraldzakwan/debugging_search_relevance
The repository is created as a supporting material for a seminar that I gave at Bukalapak. It functions as a "Mini" ElasticSearch that I use to demo some Search Engine basic functionalities: indexing, matching and ranking.
geraldzakwan/Final-Project-API-v1.1
geraldzakwan/nlp-fall-2019
This repository is for the COMS 4705 Natural Language Processing course assignments that I took at Columbia in Fall 2019. More on the course (this is with a different professor but the syllabus is similar): http://www.cs.columbia.edu/~mcollins/cs4705-spring2019/.
geraldzakwan/parallel-mt-inference
This repository is for the COMS 6998 Practical Deep Learning System Performance course final project that I took at Columbia (https://www.cs.columbia.edu/education/ms/fall-2020-topics-courses/#e6998010). In this project, my teammate and I investigate parallelism in NLP. We experimented on how parallelism (e.g. using multi-head attention instead of recurrent connection and splitting input for inference) affects model performance (accuracy and speed-wise). More on it here http://bit.ly/pract-dl-final-report.
geraldzakwan/columbia-journey
geraldzakwan/conv_dataset
geraldzakwan/ConvSeq2Seqv1
geraldzakwan/dl-comp-vis-final-project
geraldzakwan/dl_for_cv_fall_2020
geraldzakwan/EatFit-Backend
geraldzakwan/Final-Project
geraldzakwan/geraldzakwan.github.io
geraldzakwan/GoJekTechAppTest
geraldzakwan/golang-simple-http-get
geraldzakwan/katla-helper
geraldzakwan/keras-chatbot-web-api
Simple keras chat bot using seq2seq model with Flask serving web
geraldzakwan/LambdaMart
Python implementation of LambdaMart
geraldzakwan/machine-translation-service
Transformers translation flask API
geraldzakwan/ml-fall-2019
This repository is for the COMS 4771 Machine Learning course assignments that I took at Columbia in Fall 2019. More on the course: https://www.cs.columbia.edu/~djhsu/coms4771-f19/.
geraldzakwan/new-chatbot
geraldzakwan/nmt
TensorFlow Neural Machine Translation Tutorial
geraldzakwan/non-task-oriented-chatbot-using-seq2seq
geraldzakwan/papers
geraldzakwan/ParlAI
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
geraldzakwan/pract_dl_fall_2020
My solution for COMS6998 Practical Deep Learning System Performance course from Columbia University, taken in Fall 2020
geraldzakwan/pytorch-chatbot
Pytorch seq2seq chatbot
geraldzakwan/w4111-Databases
COMS W4111 - Introduction to Databases