Light

Thamme Gowda photo

thammegowda Goto Github PK

followers: 164.0 following: 64.0 repos: 69.0 gists: 13.0

Name: Thamme Gowda

Type: User

Company: Microsoft Translator

Bio: Researcher at @Microsoft | Previously: @ISI-NLP, @Apache, @USCDataScience @NASA

Twitter: thammegowda

Location: Redmond, WA

1632148

🔭 I’m currently working on neural machine translation, imbalanced learning
🌱 I’m currently learning …
👯 I’m looking to collaborate on …
🤔 I’m looking for help with …
💬 Ask me about … anything
📫 How to reach me: @thammegowda
😄 Pronouns: he/him/his
⚡ Fun fact: …

Tools

Research

Repo	Description	Status	Note
BotEval	BotEval	Complete✅	Paper; Demos
Cometoid	Distilling strong reference based metrics into stronger reference-less metrics	Complete✅	Paper @ WMT2023
sotastream	A streaming approach to machine translation training	Complete✅	Paper @ NLP OSS 2023
016-many-eng-v2	Many-to-English (v2)	Complete✅
015-nmt-ablation	Transformer ablation, showing that model can work without encoder.	Complete✅
014-udhr-dataset	Parallel sentence alignment from Universal Declaration of Human Rights corpus	WIP/Incomplete◒
013-nmt-codeswitching	Done	Complete✅	Paper
012-macrobert	Macro sampling in BERT	Didn’t work❌	Maybe we should revisit
011-imb-learn	Imbalanced machine learning: case studies in image recognition, text classification, and machine translation	Incomplete◒	Docs
010-hyperparam-theory	A theory on hyperparameter	Incomplete◒	Book idea! Needs more time. 🕙
009-nmt-toolkits	A survey of NMT toolkits	Incomplete◒	Lost interest
008-asr-eval-macro	Macro-averaged evaluation for automatic speech recognition	Incomplete◒	(Some positive results, but needs more evidence)
007-mt-eval-macro	Macro Average: Rare Types are Important Too	Complete✅	NAACL 2021
006-many-to-eng	Many-to-English machine translation tools, data, and pretrained models	Complete✅	ACL 2021 Demos. Demo page
005-nmt-imbalance	Finding the optimal vocabulary size for neural machine translation	Complete ✅	EMNLP 2020 Findings
005-nmt-imbalance-old	Neural machine translation with imbalanced classes	Complete ✅	Rejected from *ACL; Arxiv link
004-nmt-learning-curve	NMT learning curve revisited.	Complete ✅	Not published
image-forensics-MFSec17	An Approach for Automatic and Large Scale Image Forensics	Complete ✅	MFSec 2017
autoextractor	Clustering webpages based on structure and style similarity	Complete✅	IEEE IRI 2016

Thamme Gowda's Projects

004-nmt-learning-curve

NMT Learning Curve

005-nmt-imbalance

Finding the Optimal Vocabulary for NMT

006-many-to-eng

Machine translation of many to English

007-mt-eval-macro

MT evaluation, use macro-average because rare types are important too.

011-imb-learn

Imbalanced Learning

014-udhr-dataset

Parallel dataset, aligned from United Nations' Universal Declaration of Human Rights (UDHR)

015-nmt-ablation

Transformer NMT ablation

016-many-eng-v2

Many-English v2

202010-pytorch

Pytorch PPT for ISI

572-hw1

CSCI 572 Assignment 1

572-hw2

Home Work 2 Indexing + NER

572-hw3

A web-app for displaying indexed weapons data from Solr

asciidoc-book

Asciidoc book template

autoextractor

A toolkit for clustering web pages based on various similarity measures.

awkg

awkg is an awk-like text-processing tool powered by python language

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

bulrush

A Bulma-based Pelican blog theme; clean, flexible and responsive.

charliebot

The ALICE/ALICEBOT/CHARLIE/CHARLIEBOT

comet

A Neural Framework for MT Evaluation

cs561s16

Foundations of Artificial Intelligence (USC CSCI561) Coursework for Spring 2016.

db-hw5-mapview

This project was created as part of USC Fall 2015 CSCI-585 Coursework. The main purpose of the project is to demonstrate that the the concepts of Relational Databases, JDBC and Spatial Operations.

dialog-data

Dialog Datasets

dissertation

PhD dissertation

dotfiles

easyocr

Ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai

friends

Friends Transcripts

hibernate-sync-problem

Sync issue with hibernate

hw-tex-templ

Tex template for homework submission

image-forensics-mfsec17

Automated Large Scale Image Forensics using Tika and Tensorflow

image-resize

ImageMagick based resizer script for android projects.

1
2
3

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.