Name: Computation for Indian Language Technology (CFILT)
Type: Organization
Bio: NLP Resources and Codebases released by the πΆππππ’π‘ππ‘πππ πππ πΌπππππ πΏππππ’πππ πππβππππππ¦ πΏππ @ πΌπΌπ π΅πππππ¦
Twitter: cfiltnlp
Location: India
Blog: https://www.cfilt.iitb.ac.in
Computation for Indian Language Technology (CFILT)'s Projects
Repository for code and dataset for our EMNLP 2021 paper - βSo You Think Youβre Funny?β: Rating the Humour Quotient in Standup Comedy.
Cognition-aware Cognate Detection
This repository contains the HiNER dataset released with our paper at LREC 2022
The IIT Bombay English-Hindi Parallel Corpus
Manipulating the Indian Language Topic Model Output to be appended to the training corpora for both Cartesian Product method, and Sentential approach.
IWN-En contains linked Wordnet data which was linked with the help of manual efforts by lexicographers in CFILT
This repository contains the list of unique words extracted from the IndoWordnet knowledge base.
A Python based API to access Indian language WordNets.
Siamese Feed Forward Neral Network for True Cognate Detection using Pytorch.