Discover epfl-dlab/pairformance Open Source project

Google Trends, made easy.

235

GoogleTrendsAnchorBank

The autoregressive information extraction system GenIE (Generative Information Extraction) implemented in PyTorch.

101

GenIE

🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers

transformers-CFG

The data and the PyTorch implementation for the models and experiments in the paper "Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction".

SynthIE

Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

llm-latent-language

Language-Agnostic Website Embedding and Classification

homepage2vec

The data and implementation for the experiments in the paper "Flows: Building Blocks of Reasoning and Collaborating AI".

cc_flows

Code and data for the WSDM '19 paper "Crosslingual Document Embedding as Reduced-Rank Ridge Regression (Cr5)"

Cr5

GPTurk

Unsupervised method for extracting quotation-speaker pairs from large news corpora.

quootstrap

GCD

Code for the dataset paper: "YouNiverse: Large-Scale Channel and Video Metadata from English-Speaking YouTube"

YouNiverse

Code and data for the WSDM '21 paper "Quotebank: A Corpus of Quotations from a Decade of News"

Quotebank

This is a repo containing all code and steps taken to download, setup the process and convert the whole English Wikipedia history from Wikitext to HTML format.

WikiHist.html

PHP

understanding-decoding

The data and the PyTorch implementation for the models and experiments in the paper "Language Model Decoding as Likelihood–Utility Alignment".

LAMEN

Source code for "A Critical Re-evaluation of Neural Methods for Entity Alignment"

entity-matchers

Crosslingual Topic Modeling with WikiPDA

WikiPDA

Code and data for the AAAI'19 paper "Reverse-Engineering Satire, or 'Paper on Computational Humor Accepted Despite Making Serious Advances'"

unfun

A framework to train language models to learn invariant representations.

invariant-language-models

Source code for "Low-rank Subspaces for Unsupervised Entity Linking"

eigenthemes

causal-distances

Modular framework for property inference attacks on deep neural networks

property-inference-attacks

Implementation of "A fast and effective heuristic for the feedback arc set problem"

GraphCyclesRemoval

The server to collect user data and learn an SVM in the SecVM project

secvm-server

KLearn

Code to reproduce experiments of the ACL 2021 publication on the evaluation of NLP systems with the BT mechanism

BT-eval

Code for the Paper "United States Politicians' Tone Became More Negative with 2016 Primary Campaigns"

Negativity_in_2016_campaign

TeX

flows

The flows library

This repo contains the simulation code for the paper "The Amplification Paradox in Recommender Systems"

amplification_paradox

llm-grounding-analysis

Distribution Inference Risks: Identifying and Mitigating Sources of Leakage

distribution-inference-risks

Data and code for the paper "Sudden Attention Shifts on Wikipedia During the COVID-19 Crisis"

wiki_pageviews_covid

The PyTorch implementation for the models in the paper "Descartes: Generating Short Descriptions of Wikipedia Articles"

descartes

nelight

Code for the laughing head paper

laughing-head

Code and data for the paper: "Message Distortion in Information Cascades" (TheWebConf2019)

mdic

Wikipedia Image Classification project

wiki_image_classification

YouTube channel embeddings and social dimensions

youtube-embeddings

Repository for the paper “How Constraints Affect Content: The Case of Twitter's Switch from 140 to 280” published at ICWSM’18

140_to_280

WikipediaAsWebGateway

Framework for Cost-Effective Language Model Choice

CELMOC

Scripts for cleaning and enriching Quotebank

quotebank-toolkit

post-mortem-memory

broccoli-plugin

Structuring Wikipedia Articles with Section Recommendations

structuring-wikipedia-articles

foodle-trends

Repository for the article "When Sheep Shop: Measuring Herding Effects in Product Ratings with Natural Experiments" published at WWW2018

when_sheep_shop

manosphere_to_altright

DIPPS

anticipated-vs-actual

deplatforming_dataset

Repository of code and data for the paper "The effect of spokesperson attribution on public health message sharing during the COVID-19 pandemic".

SpokespersonAttributionCOVID

WCNPruning

A framework to clean the Wikipedia category network.

Quantifying Engagement with Citations on Wikipedia https://arxiv.org/abs/2001.08614

wikipedia-citation-engagement