references.bib

@inproceedings{che-etal-2018-towards,
    title = "Towards Better {UD} Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation",
    author = "Che, Wanxiang  and
      Liu, Yijia  and
      Wang, Yuxuan  and
      Zheng, Bo  and
      Liu, Ting",
    booktitle = "Proceedings of CoNLL",
    year = "2018",
    url = "https://www.aclweb.org/anthology/K18-2005",
    doi = "10.18653/v1/K18-2005",
    pages = "55--64",
}

@article{radford2018improving,
  title={Improving language understanding by generative pre-training},
  author={Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya},
  url={https://www.cs.ubc.ca/~amuham01/LING530/papers/radford2018improving.pdf},
  year={2018}
}

@article{wang2019structbert,
	title={Structbert: Incorporating language structures into pre-training for deep language understanding},
	author={Wang, Wei and Bi, Bin and Yan, Ming and Wu, Chen and Bao, Zuyi and Xia, Jiangnan and Peng, Liwei and Si, Luo},
	journal={arXiv preprint arXiv:1908.04577},
	year={2019}
}

@article{raffel2019exploring,
	title={Exploring the limits of transfer learning with a unified text-to-text transformer},
	author={Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J},
	journal={arXiv preprint arXiv:1910.10683},
	year={2019}
}

@article{radford2019language,
	title={Language models are unsupervised multitask learners},
	author={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
	journal={OpenAI Blog},
	volume={1},
	number={8},
	year={2019}
}

@inproceedings{conneau2019cross,
	title={Cross-lingual language model pretraining},
	author={Conneau, Alexis and Lample, Guillaume},
	booktitle={Proceedings of NeurIPS},
	pages={7059--7069},
	year={2019}
}

@inproceedings{dong2019unified,
	title={Unified language model pre-training for natural language understanding and generation},
	author={Dong, Li and Yang, Nan and Wang, Wenhui and Wei, Furu and Liu, Xiaodong and Wang, Yu and Gao, Jianfeng and Zhou, Ming and Hon, Hsiao-Wuen},
	booktitle={Proceedings of NeurIPS},
	pages={13063--13075},
	year={2019}
}

@article{hochreiter1997long,
	title={Long short-term memory},
	author={Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
	journal={Neural computation},
	volume={9},
	number={8},
	pages={1735--1780},
	year={1997}
}

@inproceedings{peters-etal-2017-semi,
	title = "Semi-supervised sequence tagging with bidirectional language models",
	author = "Peters, Matthew  and
	Ammar, Waleed  and
	Bhagavatula, Chandra  and
	Power, Russell",
	booktitle = "Proceedings of ACL",
	year = "2017",
	url = "https://www.aclweb.org/anthology/P17-1161",
	doi = "10.18653/v1/P17-1161",
	pages = "1756--1765",
}

@inproceedings{peters-etal-2018-deep,
	title = "Deep Contextualized Word Representations",
	author = "Peters, Matthew  and
	Neumann, Mark  and
	Iyyer, Mohit  and
	Gardner, Matt  and
	Clark, Christopher  and
	Lee, Kenton  and
	Zettlemoyer, Luke",
	booktitle = "Proceedings of NAACL-HLT",
	year = "2018",
	url = "https://www.aclweb.org/anthology/N18-1202",
	doi = "10.18653/v1/N18-1202",
	pages = "2227--2237",
}

@article{liu2019roberta,
	title={Roberta: A robustly optimized bert pretraining approach},
	author={Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis, Mike and Zettlemoyer, Luke and Stoyanov, Veselin},
	journal={arXiv preprint arXiv:1907.11692},
	year={2019}
}

@inproceedings{song2019mass,
	title={MASS: Masked Sequence to Sequence Pre-training for Language Generation},
	author={Song, Kaitao and Tan, Xu and Qin, Tao and Lu, Jianfeng and Liu, Tie-Yan},
	booktitle={Proceedings of ICML},
	pages={5926--5936},
	year={2019}
}

@inproceedings{conneau-etal-2018-xnli,
	title = "{XNLI}: Evaluating Cross-lingual Sentence Representations",
	author = "Conneau, Alexis  and
	Rinott, Ruty  and
	Lample, Guillaume  and
	Williams, Adina  and
	Bowman, Samuel  and
	Schwenk, Holger  and
	Stoyanov, Veselin",
	booktitle = "Proceedings of EMNLP",
	year = "2018",
	url = "https://www.aclweb.org/anthology/D18-1269",
	doi = "10.18653/v1/D18-1269",
	pages = "2475--2485",
}

@inproceedings{zeman-etal-2018-conll,
	title = "{C}o{NLL} 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies",
	author = "Zeman, Daniel  and
	Haji{\v{c}}, Jan  and
	Popel, Martin  and
	Potthast, Martin  and
	Straka, Milan  and
	Ginter, Filip  and
	Nivre, Joakim  and
	Petrov, Slav",
	booktitle = "Proceedings of CoNLL",
	year = "2018",
	url = "https://www.aclweb.org/anthology/K18-2001",
	doi = "10.18653/v1/K18-2001",
	pages = "1--21",
}

@inproceedings{lewis-etal-2020-bart,
	title = "{BART}: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension",
	author = "Lewis, Mike  and
	Liu, Yinhan  and
	Goyal, Naman  and
	Ghazvininejad, Marjan  and
	Mohamed, Abdelrahman  and
	Levy, Omer  and
	Stoyanov, Veselin  and
	Zettlemoyer, Luke",
	booktitle = "Proceedings of ACL",
	year = "2020",
	url = "https://www.aclweb.org/anthology/2020.acl-main.703",
	doi = "10.18653/v1/2020.acl-main.703",
	pages = "7871--7880",
}

@inproceedings{conneau-etal-2020-unsupervised,
	title = "Unsupervised Cross-lingual Representation Learning at Scale",
	author = "Conneau, Alexis  and
	Khandelwal, Kartikay  and
	Goyal, Naman  and
	Chaudhary, Vishrav  and
	Wenzek, Guillaume  and
	Guzm{\'a}n, Francisco  and
	Grave, Edouard  and
	Ott, Myle  and
	Zettlemoyer, Luke  and
	Stoyanov, Veselin",
	booktitle = "Proceedings of ACL",
	year = "2020",
	url = "https://www.aclweb.org/anthology/2020.acl-main.747",
	doi = "10.18653/v1/2020.acl-main.747",
	pages = "8440--8451",
}

@article{joshi-etal-2020-spanbert,
	title = "{S}pan{BERT}: Improving Pre-training by Representing and Predicting Spans",
	author = "Joshi, Mandar  and
	Chen, Danqi  and
	Liu, Yinhan  and
	Weld, Daniel S.  and
	Zettlemoyer, Luke  and
	Levy, Omer",
	journal = "Transactions of the Association for Computational Linguistics",
	volume = "8",
	year = "2020",
	url = "https://www.aclweb.org/anthology/2020.tacl-1.5",
	doi = "10.1162/tacl_a_00300",
	pages = "64--77",
}

@inproceedings{devlin-etal-2019-bert,
	title = "{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding",
	author = "Devlin, Jacob  and
	Chang, Ming-Wei  and
	Lee, Kenton  and
	Toutanova, Kristina",
	booktitle = "Proceedings of NAACL-HLT",
	year = "2019",
	url = "https://www.aclweb.org/anthology/N19-1423",
	doi = "10.18653/v1/N19-1423",
	pages = "4171--4186",
}

@inproceedings{mulcaire-etal-2019-polyglot,
	title = "Polyglot Contextual Representations Improve Crosslingual Transfer",
	author = "Mulcaire, Phoebe  and
	Kasai, Jungo  and
	Smith, Noah A.",
	booktitle = "Proceedings of NAACL-HLT",
	year = "2019",
	url = "https://www.aclweb.org/anthology/N19-1392",
	doi = "10.18653/v1/N19-1392",
	pages = "3912--3918",
}

@inproceedings{yang2019xlnet,
	title={Xlnet: Generalized autoregressive pretraining for language understanding},
	author={Yang, Zhilin and Dai, Zihang and Yang, Yiming and Carbonell, Jaime and Salakhutdinov, Russ R and Le, Quoc V},
	booktitle={Proceedings of NeurIPS},
	pages={5753--5763},
	year={2019}
}

@inproceedings{vaswani2017attention,
	title={Attention is all you need},
	author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
	booktitle={Proceedings of NeurIPS},
	pages={5998--6008},
	year={2017}
}

@inproceedings{yang-etal-2019-paws,
	title = "{PAWS}-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification",
	author = "Yang, Yinfei  and
	Zhang, Yuan  and
	Tar, Chris  and
	Baldridge, Jason",
	booktitle = "Proceedings of EMNLP",
	year = "2019",
	url = "https://www.aclweb.org/anthology/D19-1382",
	doi = "10.18653/v1/D19-1382",
	pages = "3687--3692",
}

@inproceedings{huang-etal-2019-unicoder,
	title = "{U}nicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks",
	author = "Huang, Haoyang  and
	Liang, Yaobo  and
	Duan, Nan  and
	Gong, Ming  and
	Shou, Linjun  and
	Jiang, Daxin  and
	Zhou, Ming",
	booktitle = "Proceedings of EMNLP",
	year = "2019",
	url = "https://www.aclweb.org/anthology/D19-1252",
	doi = "10.18653/v1/D19-1252",
	pages = "2485--2494",
}

@inproceedings{smith2018offline,
	title={Offline bilingual word vectors, orthogonal transformations and the inverted softmax},
	author={Smith, Samuel L and Turban, David HP and Hamblin, Steven and Hammerla, Nils Y},
	booktitle={Proceedings of ICLR},
	year={2018}
}

@article{mikolov2013exploiting,
	title={Exploiting similarities among languages for machine translation},
	author={Mikolov, Tomas and Le, Quoc V and Sutskever, Ilya},
	journal={arXiv preprint arXiv:1309.4168},
	year={2013}
}

@inproceedings{duh-etal-2011-machine,
	title = "Is Machine Translation Ripe for Cross-Lingual Sentiment Classification?",
	author = "Duh, Kevin  and
	Fujino, Akinori  and
	Nagata, Masaaki",
	booktitle = "Proceedings of ACL",
	year = "2011",
	url = "https://www.aclweb.org/anthology/P11-2075",
	pages = "429--433",
}

@inproceedings{faruqui-dyer-2014-improving,
	title = "Improving Vector Space Word Representations Using Multilingual Correlation",
	author = "Faruqui, Manaal  and
	Dyer, Chris",
	booktitle = "Proceedings of EACL",
	year = "2014",
	url = "https://www.aclweb.org/anthology/E14-1049",
	doi = "10.3115/v1/E14-1049",
	pages = "462--471",
}

@inproceedings{cao2020multilingual,
	title={Multilingual Alignment of Contextual Word Representations},
	author={Steven Cao and Nikita Kitaev and Dan Klein},
	booktitle={Proceedings of ICLR},
	year={2020},
	url={https://openreview.net/forum?id=r1xCMyBtPS}
}

@inproceedings{banea-etal-2008-multilingual,
	title = "Multilingual Subjectivity Analysis Using Machine Translation",
	author = "Banea, Carmen  and
	Mihalcea, Rada  and
	Wiebe, Janyce  and
	Hassan, Samer",
	booktitle = "Proceedings of EMNLP",
	year = "2008",
	url = "https://www.aclweb.org/anthology/D08-1014",
	pages = "127--135",
}

@inproceedings{pires-etal-2019-multilingual,
	title = "How Multilingual is Multilingual {BERT}?",
	author = "Pires, Telmo  and
	Schlinger, Eva  and
	Garrette, Dan",
	booktitle = "Proceedings of ACL",
	year = "2019",
	url = "https://www.aclweb.org/anthology/P19-1493",
	doi = "10.18653/v1/P19-1493",
	pages = "4996--5001"
}

@inproceedings{wu-dredze-2019-beto,
	title = "Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of {BERT}",
	author = "Wu, Shijie  and
	Dredze, Mark",
	booktitle = "Proceedings of EMNLP",
	year = "2019",
	url = "https://www.aclweb.org/anthology/D19-1077",
	doi = "10.18653/v1/D19-1077",
	pages = "833--844",
}

@inproceedings{keung-etal-2019-adversarial,
	title = "Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and {NER}",
	author = "Keung, Phillip  and
	Lu, Yichao  and
	Bhardwaj, Vikas",
	booktitle = "Proceedings of EMNLP",
	year = "2019",
	url = "https://www.aclweb.org/anthology/D19-1138",
	doi = "10.18653/v1/D19-1138",
	pages = "1355--1360",
}

@inproceedings{artetxe-etal-2020-cross,
	title = "On the Cross-lingual Transferability of Monolingual Representations",
	author = "Artetxe, Mikel  and
	Ruder, Sebastian  and
	Yogatama, Dani",
	booktitle = "Proceedings of ACL",
	year = "2020",
	url = "https://www.aclweb.org/anthology/2020.acl-main.421",
	doi = "10.18653/v1/2020.acl-main.421",
	pages = "4623--4637",
}

@inproceedings{liu-etal-2019-xqa,
	title = "{XQA}: A Cross-lingual Open-domain Question Answering Dataset",
	author = "Liu, Jiahua  and
	Lin, Yankai  and
	Liu, Zhiyuan  and
	Sun, Maosong",
	booktitle = "Proceedings of ACL",
	year = "2019",
	url = "https://www.aclweb.org/anthology/P19-1227",
	doi = "10.18653/v1/P19-1227",
	pages = "2358--2368",
}

@inproceedings{schwenk-li-2018-corpus,
	title = "A Corpus for Multilingual Document Classification in Eight Languages",
	author = "Schwenk, Holger  and
	Li, Xian",
	booktitle = "Proceedings of LREC",
	year = "2018",
	url = "https://www.aclweb.org/anthology/L18-1560",
}

@inproceedings{prettenhofer-stein-2010-cross,
	title = "Cross-Language Text Classification Using Structural Correspondence Learning",
	author = "Prettenhofer, Peter  and
	Stein, Benno",
	booktitle = "Proceedings of ACL",
	year = "2010",
	url = "https://www.aclweb.org/anthology/P10-1114",
	pages = "1118--1127",
}

@inproceedings{clark2020electra,
	title={Electra: Pre-training text encoders as discriminators rather than generators},
	author={Clark, Kevin and Luong, Minh-Thang and Le, Quoc V and Manning, Christopher D},
	booktitle={Proceedings of ICLR},
	url={https://openreview.net/forum?id=r1xMH1BtvB},
	year={2020}
}