Anoop Kunchukuttan

indic_nlp_library. Resources and tools for Indian language Natural Language Processing

indic_nlp_resources. Resources to go with the Indic NLP Library

crowd-indic-transliteration-data. Xlit-Crowd: Hindi-English Transliteration Corpus

geomm. Geometry-aware Multilingual Embeddings

multinmt_tutorial_coling2020. Material for the COLING 2020 Tutorial on Multilingual NMT

mlxlit. A Multilingual Neural Machine Transliteration System

indowordnet_parallel. Parallel corpus mined from IndoWordnet synset gloss and examples

transliterator. Unsupervised Transliterator using phonetic features (particularly for Indian languages)

multilingual_extend_llm.

meteor_indic. METEOR for Indian languages (originally forked from METEOR 1.4)

directl-p. The DirecTL+ transliteration system: Automatically exported from code.google.com/p/directl-p

cfilt_preorder. Rule based source reordering system for English-Indian language translation

news_evaluation_script. NEWS shared task evaluation script (ported to Python 3)

moses_job_scripts. A simple experiment management system for Moses

huggingface_notebooks. Notebooks using the Hugging Face libraries 🤗

indic_transliteration_analysis.

sacreBLEU-Indic. Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

UnsupervisedMT. Phrase-Based & Neural Unsupervised Machine Translation

OpenNMT-tf. My customizations to OpenNMT-tf

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

mctorch. A manifold optimization library for deep learning

DataAugForLRL. Generalized Data Augmentation for Low-Resource Translation