Pinned Repositories
borderlines
Repository for the NAACL 2024 paper "This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models"
bordIRlines
Repository for the arXiv 2024 paper "BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation"
cantonese-asr-kaldi
Code for paper " Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin"
CartoonGAN-4731
Cartoon Style Transfer for Disney films based on CartoonGAN
cis2
Code for Paper "CIS^2: A Simplified Commonsense Inference Evaluation for Story Prose"
EcXTra
Code for paper "Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation"
novel-chapter-dataset
Dataset for Paper "Exploring Content Selection in Summarization of Novel Chapters"
novel-chapter-lists
Novel Chapter Dataset
NPR-Corpus-Project
Web app that allows for searches on a dynamic corpus of conversational transcripts from NPR
paxqa
Code and Data for "PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale" (EMNLP 2023)
manestay's Repositories
manestay/novel-chapter-dataset
Dataset for Paper "Exploring Content Selection in Summarization of Novel Chapters"
manestay/cantonese-asr-kaldi
Code for paper " Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin"
manestay/borderlines
Repository for the NAACL 2024 paper "This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models"
manestay/CartoonGAN-4731
Cartoon Style Transfer for Disney films based on CartoonGAN
manestay/novel-chapter-lists
Novel Chapter Dataset
manestay/NPR-Corpus-Project
Web app that allows for searches on a dynamic corpus of conversational transcripts from NPR
manestay/paxqa
Code and Data for "PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale" (EMNLP 2023)
manestay/cis2
Code for Paper "CIS^2: A Simplified Commonsense Inference Evaluation for Story Prose"
manestay/supah-hot-fire-watcher
penn apps 2017
manestay/Asobo--The-Caring-Lifesaving-Toy
1st place at Tricontinental Hackathon at Ecole Polytechique.
manestay/bordIRlines
Repository for the arXiv 2024 paper "BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation"
manestay/EcXTra
Code for paper "Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation"
manestay/Text-to-Speech-Prosody-Project
Research with Columbia Speech Lab
manestay/crowdsourcing-class.github.io
Crowdsourcing and Human Computation (UPenn NETS 213)
manestay/cs4111-group6
Student Discount Database
manestay/glucose
GLUCOSE: GeneraLized and COntextualized Story Explanations https://arxiv.org/abs/2009.07758
manestay/hotpot_ir
manestay/im2recipe
Code supporting the CVPR 2017 paper "Learning Cross-modal Embeddings for Cooking Recipes and Food Images"
manestay/kaldi
This is now the official location of the Kaldi project.
manestay/keras
Deep Learning library for Python. Runs on TensorFlow, Theano, or CNTK.
manestay/manestay.github.io
personal website
manestay/misc-scraping-scripts
several basic scripts written to scrape healthcare and policy information
manestay/model_coevolution_language_mindreading
In this repository you can find all the Python code I used to implement my Bayesian model of the co-evolution of language and mindreading (including development, iterated learning and biological evolution).
manestay/models
Models and examples built with TensorFlow
manestay/pet-images
some pet images
manestay/pixczar
manestay/SPDR-Searcher
A webpage that searches SPDR funds from given ETF symbol and returns information and graphs.
manestay/summary-qg
Code for the ACL 2022 Paper "A Feasibility Study of Answer-Agnostic Question Generation for Education"
manestay/wals
The World Atlas of Language Structures
manestay/zero-shot-mt-pub
Zero Shot Neural Machine Translation