ai_platform_report/ref.bib

@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}
}

@inproceedings{2017Attention,
	title={Attention Is All You Need},
	author={ Vaswani, A.  and  Shazeer, N.  and  Parmar, N.  and  Uszkoreit, J.  and  Jones, L.  and  Gomez, A. N.  and  Kaiser, L.  and  Polosukhin, I. },
	booktitle={arXiv},
	year={2017},
}

@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{2019NEZHA,
	title={NEZHA: Neural Contextualized Representation for Chinese Language Understanding},
	author={ Wei, J.  and  Ren, X.  and  Li, X.  and  Huang, W.  and  Liao, Y.  and  Wang, Y.  and  Lin, J.  and  Jiang, X.  and  Chen, X.  and  Liu, Q. },
	year={2019},
}