258 lines
9.0 KiB
BibTeX
258 lines
9.0 KiB
BibTeX
@article{lecun1995convolutional,
|
||
title={Convolutional networks for images, speech, and time series},
|
||
author={LeCun, Yann and Bengio, Yoshua and others},
|
||
journal={The handbook of brain theory and neural networks},
|
||
volume={3361},
|
||
number={10},
|
||
pages={1995},
|
||
year={1995},
|
||
publisher={Cambridge, MA USA}
|
||
}
|
||
|
||
@article{2017Attention,
|
||
author = {Ashish Vaswani and
|
||
Noam Shazeer and
|
||
Niki Parmar and
|
||
Jakob Uszkoreit and
|
||
Llion Jones and
|
||
Aidan N. Gomez and
|
||
Lukasz Kaiser and
|
||
Illia Polosukhin},
|
||
title = {Attention Is All You Need},
|
||
journal = {CoRR},
|
||
volume = {abs/1706.03762},
|
||
year = {2017},
|
||
url = {http://arxiv.org/abs/1706.03762},
|
||
eprinttype = {arXiv},
|
||
eprint = {1706.03762},
|
||
timestamp = {Sat, 23 Jan 2021 01:20:40 +0100},
|
||
biburl = {https://dblp.org/rec/journals/corr/VaswaniSPUJGKP17.bib},
|
||
bibsource = {dblp computer science bibliography, https://dblp.org}
|
||
}
|
||
|
||
@online{kexuefm-7718,
|
||
title={动手做个DialoGPT：基于LM的生成式多轮对话模型},
|
||
author={苏剑林},
|
||
year={2020},
|
||
month={Sep},
|
||
howpublished={\url{https://spaces.ac.cn/archives/7718}},
|
||
}
|
||
|
||
@online{kaggle,
|
||
title={House Prices - Advanced Regression Techniques},
|
||
howpublished={\url{https://www.kaggle.com/competitions/house-prices-advanced-regression-techniques/overview}},
|
||
}
|
||
|
||
@online{aliyun2018pose,
|
||
title={计算机视觉方向简介 | 人体骨骼关键点检测综述},
|
||
howpublished={\url{https://developer.aliyun.com/article/639017}},
|
||
}
|
||
|
||
@article{2020UNet,
|
||
title={UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation},
|
||
author={ Zhou, Z. and Siddiquee, Mmr and Tajbakhsh, N. and Liang, J. },
|
||
journal={IEEE Transactions on Medical Imaging},
|
||
volume={39},
|
||
number={6},
|
||
pages={1856-1867},
|
||
year={2020},
|
||
}
|
||
@dataset{jiang_hou_2021_5171712,
|
||
author = {Jiang Hou and
|
||
Yao Ling and
|
||
Liu Yujun},
|
||
title = {{Multi-resolution dataset for photovoltaic panel
|
||
segmentation from satellite and aerial imagery}},
|
||
month = aug,
|
||
year = 2021,
|
||
note = {{Data document can refer to the preprint https://es
|
||
sd.copernicus.org/preprints/essd-2021-270/}},
|
||
publisher = {Zenodo},
|
||
version = {v1.0},
|
||
doi = {10.5281/zenodo.5171712},
|
||
url = {https://doi.org/10.5281/zenodo.5171712}
|
||
}
|
||
@article{devlin2018bert,
|
||
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
|
||
author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
|
||
journal={arXiv preprint arXiv:1810.04805},
|
||
year={2018}
|
||
}
|
||
@inproceedings{radford2021learning,
|
||
title={Learning transferable visual models from natural language supervision},
|
||
author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others},
|
||
booktitle={International Conference on Machine Learning},
|
||
pages={8748--8763},
|
||
year={2021},
|
||
organization={PMLR}
|
||
}
|
||
@inproceedings{wang2020large,
|
||
title={A large-scale chinese short-text conversation dataset},
|
||
author={Wang, Yida and Ke, Pei and Zheng, Yinhe and Huang, Kaili and Jiang, Yong and Zhu, Xiaoyan and Huang, Minlie},
|
||
booktitle={CCF International Conference on Natural Language Processing and Chinese Computing},
|
||
pages={91--103},
|
||
year={2020},
|
||
organization={Springer}
|
||
}
|
||
@article{liu2017order,
|
||
title={In-order transition-based constituent parsing},
|
||
author={Liu, Jiangming and Zhang, Yue},
|
||
journal={Transactions of the Association for Computational Linguistics},
|
||
volume={5},
|
||
pages={413--424},
|
||
year={2017},
|
||
publisher={MIT Press}
|
||
}
|
||
@inproceedings{he-choi-2021-stem,
|
||
title = "The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders",
|
||
author = "He, Han and Choi, Jinho D.",
|
||
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
|
||
month = nov,
|
||
year = "2021",
|
||
address = "Online and Punta Cana, Dominican Republic",
|
||
publisher = "Association for Computational Linguistics",
|
||
url = "https://aclanthology.org/2021.emnlp-main.451",
|
||
pages = "5555--5577",
|
||
abstract = "Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks that are distinct in nature. We first present MTL results on five NLP tasks, POS, NER, DEP, CON, and SRL, and depict its deficiency over single-task learning. We then conduct an extensive pruning analysis to show that a certain set of attention heads get claimed by most tasks during MTL, who interfere with one another to fine-tune those heads for their own objectives. Based on this finding, we propose the Stem Cell Hypothesis to reveal the existence of attention heads naturally talented for many tasks that cannot be jointly trained to create adequate embeddings for all of those tasks. Finally, we design novel parameter-free probes to justify our hypothesis and demonstrate how attention heads are transformed across the five tasks during MTL through label analysis.",
|
||
}
|
||
@online{zhinengyuyindongcha2020,
|
||
title={智能语音专题（一）：智能语音交互的概念},
|
||
howpublished={\url{https://zhuanlan.zhihu.com/p/109885562}},
|
||
}
|
||
|
||
@inproceedings{yao2021wenet,
|
||
title={WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit},
|
||
author={Yao, Zhuoyuan and Wu, Di and Wang, Xiong and Zhang, Binbin and Yu, Fan and Yang, Chao and Peng, Zhendong and Chen, Xiaoyu and Xie, Lei and Lei, Xin},
|
||
booktitle={Proc. Interspeech},
|
||
year={2021},
|
||
address={Brno, Czech Republic },
|
||
organization={IEEE}
|
||
}
|
||
@article{Wei2019NEZHA,
|
||
author = {Junqiu Wei and
|
||
Xiaozhe Ren and
|
||
Xiaoguang Li and
|
||
Wenyong Huang and
|
||
Yi Liao and
|
||
Yasheng Wang and
|
||
Jiashu Lin and
|
||
Xin Jiang and
|
||
Xiao Chen and
|
||
Qun Liu},
|
||
title = {{NEZHA:} Neural Contextualized Representation for Chinese Language
|
||
Understanding},
|
||
journal = {CoRR},
|
||
volume = {abs/1909.00204},
|
||
year = {2019},
|
||
url = {http://arxiv.org/abs/1909.00204},
|
||
eprinttype = {arXiv},
|
||
eprint = {1909.00204},
|
||
timestamp = {Tue, 21 Dec 2021 15:05:23 +0100},
|
||
biburl = {https://dblp.org/rec/journals/corr/abs-1909-00204.bib},
|
||
bibsource = {dblp computer science bibliography, https://dblp.org}
|
||
}
|
||
@online{kexuefm-7148,
|
||
title={“非自回归”也不差：基于MLM的阅读理解问答},
|
||
author={苏剑林},
|
||
year={2019},
|
||
month={Dec},
|
||
howpublished={\url{https://spaces.ac.cn/archives/7148}},
|
||
}
|
||
|
||
@article{Li2016Dataset,
|
||
title={Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering},
|
||
author={ Li, P. and Li, W. and He, Z. and Wang, X. and Cao, Y. and Zhou, J. and Xu, W. },
|
||
year={2016},
|
||
}
|
||
@online{cips2018sogou,
|
||
title={CIPS-SOGOU问答比赛},
|
||
howpublished={\url{http://task.www.sogou.com/cips-sogou_qa/}},
|
||
}
|
||
@misc{myhub2021tr,
|
||
author={myhub},
|
||
title={{tr - Text Recognition}},
|
||
version={2.3.1},
|
||
month=dec,
|
||
year=2021,
|
||
publisher={GithubRepository},
|
||
howpublished={\url{github.com/myhub/tr}},
|
||
}
|
||
|
||
@article{Redmon2015YOLO,
|
||
author = {Joseph Redmon and
|
||
Santosh Kumar Divvala and
|
||
Ross B. Girshick and
|
||
Ali Farhadi},
|
||
title = {You Only Look Once: Unified, Real-Time Object Detection},
|
||
journal = {CoRR},
|
||
volume = {abs/1506.02640},
|
||
year = {2015},
|
||
url = {http://arxiv.org/abs/1506.02640},
|
||
eprinttype = {arXiv},
|
||
eprint = {1506.02640},
|
||
timestamp = {Mon, 13 Aug 2018 16:48:08 +0200},
|
||
biburl = {https://dblp.org/rec/journals/corr/RedmonDGF15.bib},
|
||
bibsource = {dblp computer science bibliography, https://dblp.org}
|
||
}
|
||
|
||
@software{glenn_jocher_2022_7002879,
|
||
author = {Glenn Jocher and
|
||
Ayush Chaurasia and
|
||
Alex Stoken and
|
||
Jirka Borovec and
|
||
NanoCode012 and
|
||
Yonghye Kwon and
|
||
TaoXie and
|
||
Kalen Michael and
|
||
Jiacong Fang and
|
||
imyhxy and
|
||
Lorna and
|
||
Colin Wong and
|
||
曾逸夫(Zeng Yifu) and
|
||
Abhiram V and
|
||
Diego Montes and
|
||
Zhiqiang Wang and
|
||
Cristi Fati and
|
||
Jebastin Nadar and
|
||
Laughing and
|
||
UnglvKitDe and
|
||
tkianai and
|
||
yxNONG and
|
||
Piotr Skalski and
|
||
Adam Hogan and
|
||
Max Strobel and
|
||
Mrinal Jain and
|
||
Lorenzo Mammana and
|
||
xylieong},
|
||
title = {{ultralytics/yolov5: v6.2 - YOLOv5 Classification
|
||
Models, Apple M1, Reproducibility, ClearML and
|
||
Deci.ai integrations}},
|
||
month = aug,
|
||
year = 2022,
|
||
publisher = {Zenodo},
|
||
version = {v6.2},
|
||
doi = {10.5281/zenodo.7002879},
|
||
url = {https://doi.org/10.5281/zenodo.7002879}
|
||
}
|
||
|
||
@article{Taylor2018Forecasting,
|
||
title={Forecasting at Scale},
|
||
author={Taylor and Sean and J. and Letham and Benjamin},
|
||
journal={American Statistician},
|
||
year={2018},
|
||
}
|
||
|
||
@article{chen2016xgboost,
|
||
author = {Tianqi Chen and
|
||
Carlos Guestrin},
|
||
title = {XGBoost: {A} Scalable Tree Boosting System},
|
||
journal = {CoRR},
|
||
volume = {abs/1603.02754},
|
||
year = {2016},
|
||
url = {http://arxiv.org/abs/1603.02754},
|
||
eprinttype = {arXiv},
|
||
eprint = {1603.02754},
|
||
timestamp = {Mon, 13 Aug 2018 16:47:00 +0200},
|
||
biburl = {https://dblp.org/rec/journals/corr/ChenG16.bib},
|
||
bibsource = {dblp computer science bibliography, https://dblp.org}
|
||
} |