dayihengliu Goto Github PK

a2m_chinesenmt

Dataset for TALLIP2019 paper "Ancient-Modern Chinese Translation with a New Large Training Dataset"

awesome-text-summarization

The guide to tackle with the Text Summarization

bert-related-papers

BERT-related papers

bert-whitening

简单的向量白化改善句向量质量

chinese-poetry

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。 阿里招 Python P6/P7 上海张江, [email protected]

cnn-dailymail

Code to obtain the CNN / Daily Mail dataset (non-anonymized) for summarization (Python3)

crqda

Code for EMNLP2020 paper: "Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space"

datasets

🤗 Fast, efficient, open-access datasets and evaluation metrics for Natural Language Processing and more in PyTorch, TensorFlow, NumPy and Pandas

dayihengliu.github.io

Personal website https://dayihengliu.github.io/

fine-grained-style-transfer

Code for AAAI2020 paper: "Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning"

glge

GLGE: A New General Language Generation Evaluation Benchmark

go

<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.

jittor

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

keymultiheadline

Code for EMNLP2020 paper: "Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation"

longformer

Longformer: The Long-Document Transformer

mass

MASS: Masked Sequence to Sequence Pre-training for Language Generation

mu-forcing-vrae

Code for TALLIP2019 paper "µ-Forcing: Training Variational Recurrent Autoencoders for Text Generation"

nlg-researchers

本文旨在整理文本生成领域国内外工业界和企业家的研究者和研究机构。排名不分先后。更新中，欢迎大家补充

prophetnet

ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training https://arxiv.org/pdf/2001.04063.pdf

research

novel deep learning research works with PaddlePaddle

research-1

responsiblenlpresearch

templates and other documents regarding responsible NLP research

text-infilling-gradient-search

Code for ACL2019 paper: "TIGS: An Inference Algorithm for Text Infilling with Gradient Search"

unicoder

Unicoder model for understanding and generation.

xglue

Cross-lingual GLUE

xsum

Topic-Aware Convolutional Neural Networks for Extreme Summarization

xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.