model¶
文本摘要¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
Extractive Summarization as Text Matching |
Fudan University |
Ming Zhong |
Extractive Summarization as Text Matching |
2020 |
Python |
PyTorch |
240 |
51 |
23 |
||
Text Summarization with Pretrained Encoders |
University of Edinburgh |
Yang Liu |
Text Summarization with Pretrained Encoders |
2019 |
Python 3.6 |
PyTorch 1.1.0 |
825 |
325 |
233 |
||
GSum |
Carnegie Mellon University |
Zi-Yi Dou |
GSum: A General Framework for Guided Neural Abstractive Summarization |
2020 |
None |
None |
14 |
1 |
1 |
||
ProphetNet |
University of Science and Technology of China,Microsoft,Microsoft Research Asia,Sichuan University |
Weizhen Qi |
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training |
2020 |
Python |
torch==1.3.0 fairseq==v0.9.0 |
229 |
44 |
34 |
||
Controlling the Amount of Verbatim Copying in Abstractive Summarization |
University of Central Florida,Robert Bosch LLC |
Kaiqiang Song |
Controlling the Amount of Verbatim Copying in Abstractive Summarization |
2020 |
Python 3.7 |
Pytorchv1.3 Pyrouge pytorch-pretrained-bert |
33 |
7 |
7 |
||
PEGASUS |
Imperial College London,Google Research |
Jingqing Zhang |
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization |
2020 |
Python |
Google Cloud or gsutil |
915 |
180 |
93 |
||
UNILM |
Microsoft Research |
Li Dong |
Unified Language Model Pre-training for Natural Language Understanding and Generation |
2019 |
Python |
UniLM v1 |
1723 |
371 |
305 |
||
BART |
Facebook AI |
Mike Lewis |
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension |
2019 |
Python |
Pytorch |
10.9k |
2.8k |
392 |
||
ALONE |
Tokyo Institute of Technology,Tohoku University |
Sho Takase |
All Word Embeddings from One Embedding |
2020 |
Python>=3.6 |
Pytorch>=1.4.0 |
17 |
1 |
1 |
||
Learning to Extract Coherent Summary via Deep Reinforcement Learning |
Hong Kong University of Science and Technology,University of Massachusetts Medical School |
YuxiangWu |
查看 |
Learning to Extract Coherent Summary via Deep Reinforcement Learning |
2018 |
Null |
Null |
Null |
Null |
58 |
|
Extractive Summarization with SWAP-NET |
Indian Institute of Science,School of Computing National University of Singapore |
Aishwarya Jadhav |
查看 |
Extractive Summarization with SWAP-NET:Sentences and Words from Alternating Pointer Networks |
2018 |
Null |
Null |
Null |
Null |
39 |
自然语言推理¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
Transformer-XH |
University of Maryland, College Park,Microsoft AI & Research |
Chen Zhao |
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention |
2019 |
Python |
NVIDIA apex |
52 |
12 |
21 |
||
XLNet |
Carnegie Mellon University,Google AI Brain Team |
Zhilin Yang |
Generalized Autoregressive Pretraining for Language Understanding |
2019 |
Python2 |
TensorFlow 1.13.1 |
5.5k |
1.1k |
1906 |
||
RoBERTa |
Paul G. Allen School of Computer Science & Engineering University of Washington,Facebook AI |
Yinhan Liu |
RoBERTa: A Robustly Optimized BERT Pretraining Approach |
2019 |
Python>=3.6 |
PyTorch>= 1.5.NVIDIA GPUNCCL |
11k |
2.8k |
686 |
||
BERT |
Google AI Language |
Jacob Devlin |
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding |
2019 |
Python |
TensorFlow |
26.6k |
7.5k |
14563 |
||
SAE |
JD AI Research |
Ming Tu |
Select, Answer and Explain: Interpretable Multi-Hop Reading Comprehension over Multiple Documents |
2020 |
Python |
PyTorch >= 1.1 |
22 |
3 |
22 |
||
DFGN |
Shanghai Jiao Tong University,ByteDance AI Lab, China |
Lin Qiu |
Dynamically Fused Graph Network for Multi-hop Reasoning |
2019 |
Python3 |
PyTorch0.4.1boto3 |
158 |
31 |
35 |
||
ALBERT |
Google Research,Toyota Technological Institute at Chicago |
Zhenzhong Lan |
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations |
2019 |
Python |
PyTorch |
2.6k |
475 |
1093 |
||
GPT |
OpenAI |
Alec Radford |
Improving Language Understanding by Generative Pre-Training |
2018 |
Python |
ftfy==4.4.3spacy |
1.6k |
419 |
1844 |
||
MPNet |
Nanjing University of Science and Technology,Microsoft Research |
Kaitao Song |
MPNet: Masked and Permuted Pre-training for Language Understanding |
2020 |
Python |
pytorch_transformers==1.0.0transformersscipysklearn |
162 |
18 |
8 |
||
Longformer |
Allen Institute for Artificial Intelligence |
Iz Beltagy |
Longformer: The Long-Document Transformer |
2020 |
Python 3.7 |
cudatoolkit=10.0 |
1k |
125 |
166 |
||
DPR |
Facebook AI,University of Washington,Princeton University |
Vladimir Karpukhin |
Dense Passage Retrieval for Open-Domain Question Answering |
2020 |
Python 3.6+ |
PyTorch 1.2.0+ |
477 |
84 |
37 |
Image Captioning¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
VirTex |
University of Michigan |
Karan Desai |
VirTex: Learning Visual Representations from Textual Annotations |
2021 |
Python 3.6+ |
PyTorch 1.2.0+ |
330 |
31 |
10 |
||
Bottom-up and Top-down Attention |
Australian National University,Microsoft Research,University of Adelaide,Macquarie University |
Peter Anderson |
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering |
2018 |
Python 3.6 |
Pytorch 0.4.1 |
115 |
28 |
1564 |
||
VC R-CNN |
University of Electronic Science and Technology of China,Damo Academy, Alibaba Group,Nanyang Technological University,Singapore Management University |
Tan Wang |
Visual Commonsense R-CNN |
2020 |
Python 3.7 |
Pytorch 1.0 |
255 |
37 |
15 |
||
AoA |
School of Electronic and Computer Engineering, Peking University,Peng Cheng Laboratory,Macau University of Science and Technology |
Lun Huang |
Attention on Attention for Image Captioning |
2019 |
Python 3.6 |
PyTorch 1.0 |
229 |
50 |
99 |
||
Improving IC |
Ingenuity Labs Research Institute, Queen’s University,Department of Electrical and Computer Engineering, Queen’s University,School of Computer Science, Fudan University |
Zhan Shi |
Improving Image Captioning with Better Use of Captions |
2020 |
Python 2.7.15 |
Torch 1.0.1 |
16 |
5 |
1 |
||
Self-Attention Network |
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,School of Artificial Intelligence, University of Chinese Academy of Sciences,University of Science and Technology Beijing,Wuhan University |
Longteng Guo |
Normalized and Geometry-Aware Self-Attention Network for Image Captioning |
2020 |
None |
None |
None |
None |
4 |
||
Meshed-Memory Transformer |
University of Modena and Reggio Emilia |
Marcella Cornia |
Meshed-Memory Transformer for Image Captioning |
2020 |
Python 3.6 |
Pytorch |
194 |
42 |
39 |
||
X-Linear Attention Networks |
JD AI Research, Beijing, China |
Yingwei Pan |
X-Linear Attention Networks for Image Captioning |
2020 |
Python 3 |
PyTorch (>1.0) |
157 |
20 |
32 |
||
Oscar |
Microsoft Corporation,University of Washington |
Xiujun Li |
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks |
2020 |
Python |
Pytorch |
279 |
55 |
28 |
NER¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
LUKE |
Studio Ousia,RIKEN AIP,University of Washington,Nara Institute of Science and Technology,National Institute of Informatics |
Ikuya Yamada |
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention |
2020 |
Python |
Pytorch |
149 |
16 |
5 |
||
MRC Framework |
Department of Computer Science and Technology, Zhejiang University,Shannon.AI |
Xiaoya Li |
A Unified MRC Framework for Named Entity Recognition |
2019 |
Python |
Pytorch |
103 |
26 |
45 |
||
NER as Dependency Parsing |
Queen Mary University,Google Research |
Juntao Yu |
Named Entity Recognition as Dependency Parsing |
2020 |
Python 2 |
Pytorch |
100 |
18 |
8 |
Relation Extraction¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
Joint Entity and Relation Extraction |
College of Computer Science and Technology, Zhejiang University,StatNLP Research Group, Singapore University of Technology and Design |
Jue Wang |
Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders |
2020 |
python3 |
pytorch 1.4.0 |
61 |
16 |
None |
||
Downstream Model Design |
AI Application Research Center, Huawei Technologies, Shenzhen, China |
Cheng Li |
Downstream Model Design of Pre-trained Language Model for Relation Extraction Task |
2020 |
Python |
Pytorch |
74 |
14 |
4 |
Event Extraction¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
One for All |
Alt Inc.,Department of Computer and Information Science, University of Oregon |
Trung Minh Nguyen |
One for All: Neural Joint Modeling of Entities and Events |
2019 |
None |
None |
None |
None |
33 |
Natural Language Inference¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
Self-Explaining Structures |
Zhejiang University,Computer Center of Peking University,Peng Cheng Laboratory,Shannon.AI |
Zijun Sun |
Self-Explaining Structures Improve NLP Models |
2020 |
Python |
Pytorch |
11 |
1 |
None |
||
Conditionally Adaptive Multi-Task Learning |
Polytechnique Montreal & Mila,Element AI,CIFAR AI Chair |
Jonathan Pilault |
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data |
2020 |
None |
None |
None |
None |
None |
||
Exploring the Limits of Transfer Learning |
Google, Mountain View, CA 94043, USA |
Colin Raffel |
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer |
2019 |
Python |
TensorFlow |
3113 |
421 |
575 |
Machine Reading Comprehension¶
名称 |
机构 |
作者 |
代码链接 |
论文 |
模型链接 |
年份 |
编程语言 |
运行环境 |
star |
fork |
引用 |
---|---|---|---|---|---|---|---|---|---|---|---|
SpanBERT |
Allen School of Computer Science & Engineering, University of Washington, Seattle, WA,Computer Science Department, Princeton University, Princeton, NJ,Allen Institute of Artificial Intelligence, Seattle,Facebook AI Research, Seattle |
Mandar Joshi |
SpanBERT: Improving Pre-training by Representing and Predicting Spans |
2020 |
Python |
Pytorch |
500 |
95 |
282 |
||
Hierarchical Graph Network |
Microsoft Dynamics 365 AI Research |
Yuwei Fang |
Hierarchical Graph Network for Multi-hop Question Answering |
2019 |
Python |
Pytorch |
32 |
5 |
29 |