elwintay

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Research

novel deep learning research works with PaddlePaddle

OpenOOD

Benchmarking Generalized Out-of-Distribution Detection

DensePhrases

[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624

MatchSum

Code for ACL 2020 paper: "Extractive Summarization as Text Matching"

pecos

PECOS - Prediction for Enormous and Correlated Spaces

LegalPapers

Must-read Papers on Legal Intelligence

Condenser

EMNLP 2021 - Pre-training architectures for dense retrieval

FuseDream

vila

Incorporating VIsual LAyout Structures for Scientific Text Classification

logitnorm_ood

Official code for ICML 2022: Mitigating Neural Network Overconfidence with Logit Normalization

PAIE

ACL'2022: Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

iPrompt

Code, Data and Demo for Paper: Controllable Generation from Pre-trained Language Models via Inverse Prompting

personality-prediction-from-text

Predicting big five personality traits from a given text.

torch-rgcn

A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).

text_to_table

docAMR

code for document level AMR representation and evaluation

TSAR

Source code for "A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction" @ NAACL 2022

ConfliBERT

ConfliBERT: A Pre-trained Language Model for Political Conflict and Violence (NAACL 2022)

EntEmb

Entity Embeddings

open-sampling

Official code for ICML 2022: Open-Sampling: Exploring Out-of-Distribution Data for Re-balancing Long-tailed Datasets

daseg

Dialog Acts SEGmentation: Tools for dialog act research

memory_docie

LatentEnhancement

FingerGAN: A Constrained Fingerprint Generation Scheme for Latent Fingerprint Enhancement

msg

amazon-succinct-doc-representation

crowdaq-doc

rgeoprofile

rgeoprofile: Geographic Profiling Methods for Serial Crime Analysis

steqe

Data and code for "A Meta-framework for Spatiotemporal Quantity Extraction from Text", ACL 2022

Xray-ObjSep-v1