yuxiang-wu

chatarena

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

APE

Adaptive Passage Encoder for Open-domain Question Answering

EMAT

Efficient Memory-Augmented Transformers

arxiv_preprocess

Preprocessing arxiv papers for abstractive summarization.

cnn-dailymail-summary

Proprocessing scripts for using CNN/Daily Mail as summarization dataset.

colabcode

Run VSCode (codeserver) on Google Colab or Kaggle Notebooks

EMAT

gen-debiased-nli

pythonrouge

Python implementation for evaluating summarization by ROUGE package

sgdsvm

Leon Bottou's SVM implemented with SGD

yuxiang-wu/gen-debiased-nli

yuxiang-wu/cnn-dailymail-summary

Proprocessing scripts for using CNN/Daily Mail as summarization dataset.

yuxiang-wu/arxiv_preprocess

Preprocessing arxiv papers for abstractive summarization.

yuxiang-wu/EMAT

yuxiang-wu/pythonrouge

Python implementation for evaluating summarization by ROUGE package

yuxiang-wu/skyline

Source code of "Don’t Read Too Much into it: Adaptive Computation for Open-Domain Question Answering" EMNLP2020

yuxiang-wu/colabcode

Run VSCode (codeserver) on Google Colab or Kaggle Notebooks

yuxiang-wu/annotated-transformer

http://nlp.seas.harvard.edu/2018/04/03/attention.html

yuxiang-wu/BLINK

Entity Linker solution

yuxiang-wu/chronological-map-phenotypes

Machine-readable version of electronic health record phenotypes for Kuan V. and Denaxas S. et al.

yuxiang-wu/cnn_coherence

yuxiang-wu/datasets

🤗 Fast, efficient, open-access datasets and evaluation metrics in PyTorch, TensorFlow, NumPy and Pandas

yuxiang-wu/dl4mt-tutorial

yuxiang-wu/DQN_tensorflow

Tensorflow implementation of deep Q networks in paper 'Playing Atari with Deep Reinforcement Learning'

yuxiang-wu/DrQA

Reading Wikipedia to Answer Open-Domain Questions

yuxiang-wu/hans

Heuristic Analysis for NLI Systems

yuxiang-wu/hed-dlg-truncated

Hierarchical Encoder Decoder RNN (HRED) with Truncated Backpropagation Through Time (Truncated BPTT)

yuxiang-wu/LAMA

LAnguage Model Analysis

yuxiang-wu/lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

yuxiang-wu/MulCode

yuxiang-wu/nltk

NLTK Source

yuxiang-wu/PAQ

Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"

yuxiang-wu/qangaroo

This is a repo for models designed for the QAngaroo dataset.

yuxiang-wu/SentEval

A python tool for evaluating the quality of sentence embeddings.

yuxiang-wu/sledgehammer

yuxiang-wu/stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

yuxiang-wu/tensorflow

Computation using data flow graphs for scalable machine learning

yuxiang-wu/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

yuxiang-wu/transformersX

Transformers made perfect!

yuxiang-wu/vimrc