I work on Machine Learning and NLP. I am interested in multilingual computing, Indian language NLP and machine translation.
indic_nlp_library. Resources and tools for Indian language Natural Language Processing
640indic_nlp_resources. Resources to go with the Indic NLP Library
78crowd-indic-transliteration-data. Xlit-Crowd: Hindi-English Transliteration Corpus
38geomm. Geometry-aware Multilingual Embeddings
26multinmt_tutorial_coling2020. Material for the COLING 2020 Tutorial on Multilingual NMT
16mlxlit. A Multilingual Neural Machine Transliteration System
7indowordnet_parallel. Parallel corpus mined from IndoWordnet synset gloss and examples
7transliterator. Unsupervised Transliterator using phonetic features (particularly for Indian languages)
5multilingual_extend_llm.
5meteor_indic. METEOR for Indian languages (originally forked from METEOR 1.4)
3directl-p. The DirecTL+ transliteration system: Automatically exported from code.google.com/p/directl-p
3cfilt_preorder. Rule based source reordering system for English-Indian language translation
3news_evaluation_script. NEWS shared task evaluation script (ported to Python 3)
2moses_job_scripts. A simple experiment management system for Moses
2huggingface_notebooks. Notebooks using the Hugging Face libraries 🤗
1indic_transliteration_analysis.
1sacreBLEU-Indic. Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
1UnsupervisedMT. Phrase-Based & Neural Unsupervised Machine Translation
1OpenNMT-tf. My customizations to OpenNMT-tf
1transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
1fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
1mctorch. A manifold optimization library for deep learning
1DataAugForLRL. Generalized Data Augmentation for Low-Resource Translation
1