Name: Anoop Kunchukuttan
Type: User
Company: Microsoft Translator, AI4Bharat, IIT Madras
Bio: I work on Machine Learning and NLP. I am interested in multilingual computing, Indian language NLP and machine translation.
Location: Hyderabad, India
Blog: http://anoopk.in
Anoop Kunchukuttan's Projects
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
A small python script that transliterates Arabic text using the Buckwalter Transliteration Scheme. It allows for multiple decisions to be made around whether or not to include all types of diacritics and characters or ignore them. Useful for NLP experiments where you may want to normalize text.
Rule based source reordering system for English-Indian language translation
Xlit-Crowd: Hindi-English Transliteration Corpus
Generalized Data Augmentation for Low-Resource Translation
Some explorations in deep learning, primarily with Theano
The DirecTL+ transliteration system: Automatically exported from code.google.com/p/directl-p
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Some example code related to Bayesian learning. Code written for my learning
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Geometry-aware Multilingual Embeddings
Python script for retrieving data from the Google Books Ngram Viewer. Modified from the original script at www.culturomics.org.
Library for implementing RNNs with Theano
Notebooks using the Hugging Face libraries 🤗
Scripts and configuration files for the Nematus NMT system, especially for Indian languages
Resources and tools for Indian language Natural Language Processing
Resources to go with the Indic NLP Library
Archived old website for AI4Bhārat Indic-NLP
Parallel corpus mined from IndoWordnet synset gloss and examples
Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).
A framework for few-shot evaluation of autoregressive language models.
Automatically exported from code.google.com/p/m2m-aligner
A manifold optimization library for deep learning
System Combination
Meteor Automatic Translation Evaluation System
METEOR for Indian languages (originally forked from METEOR 1.4)
Latest developments in LLM space
A Multilingual Neural Machine Transliteration System