Memory Networks implementations

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Python wrapper for Stanford CoreNLP.

The CoreNLP package is a thin Elixir client for the Stanford CoreNLP Server.

CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.

A Python library for quantum programming using Quil.

JDsearch: A Personalized Product Search Dataset with Real Queries and Full Interactions

An open-source dataset for e-commerce user intent detection and embedding retrieval

The Kyoto Text Analysis Toolkit for word segmentation and pronunciation estimation, etc.

indicTranslate v1 - Machine Translation for 11 Indic languages. For latest v2, check: https://github.com/AI4Bharat/IndicTrans2

Resources and tools for Indian language Natural Language Processing

Moses, the machine translation system

Supplementary material for "When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation?" at NAACL 2018

Hanzi Converter for Traditional and Simplified Chinese

Factoid Question Answering System - An advanced Open-domain Question Answering (ODQA) project that automatically answers factoid questions in Arabic and English languages using NLP and machine lear…

Comostional question answering

Metadata and versioning details for the Common Voice dataset

Lexical data at Unicode

Crawler for linguistic corpora

Multilingual parallel corpus based on OPUS Opensubtitles and corpus compiler

Parallel data mining with Mann-ki-Baat

Easy Bootstrap Resampling and Approximate Randomization for BLEU, METEOR, and TER using Multiple Optimizer Runs. This implements "Better Hypothesis Testing for Statistical Machine Translation: Cont…

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

A tool that locates, downloads, and extracts machine translation corpora

The Open Parallel Corpus

Stand-alone language identification system

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

Tooling to play around with multilingual machine translation for Indian Languages.