BibTeX records: Jason Phang

download as .bib file

@article{DBLP:journals/corr/abs-2402-16817,
  author       = {Jason Phang},
  title        = {Investigating the Effectiveness of HyperTuning via Gisting},
  journal      = {CoRR},
  volume       = {abs/2402.16817},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.16817},
  doi          = {10.48550/ARXIV.2402.16817},
  eprinttype    = {arXiv},
  eprint       = {2402.16817},
  timestamp    = {Mon, 25 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-16817.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/MichaelHPMWCMNP23,
  author       = {Julian Michael and
                  Ari Holtzman and
                  Alicia Parrish and
                  Aaron Mueller and
                  Alex Wang and
                  Angelica Chen and
                  Divyam Madaan and
                  Nikita Nangia and
                  Richard Yuanzhe Pang and
                  Jason Phang and
                  Samuel R. Bowman},
  editor       = {Anna Rogers and
                  Jordan L. Boyd{-}Graber and
                  Naoaki Okazaki},
  title        = {What Do {NLP} Researchers Believe? Results of the {NLP} Community
                  Metasurvey},
  booktitle    = {Proceedings of the 61st Annual Meeting of the Association for Computational
                  Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada,
                  July 9-14, 2023},
  pages        = {16334--16368},
  publisher    = {Association for Computational Linguistics},
  year         = {2023},
  url          = {https://doi.org/10.18653/v1/2023.acl-long.903},
  doi          = {10.18653/V1/2023.ACL-LONG.903},
  timestamp    = {Thu, 10 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/acl/MichaelHPMWCMNP23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/PhangZL23,
  author       = {Jason Phang and
                  Yao Zhao and
                  Peter J. Liu},
  editor       = {Houda Bouamor and
                  Juan Pino and
                  Kalika Bali},
  title        = {Investigating Efficiently Extending Transformers for Long Input Summarization},
  booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural
                  Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},
  pages        = {3946--3961},
  publisher    = {Association for Computational Linguistics},
  year         = {2023},
  url          = {https://aclanthology.org/2023.emnlp-main.240},
  timestamp    = {Wed, 13 Dec 2023 17:20:20 +0100},
  biburl       = {https://dblp.org/rec/conf/emnlp/PhangZL23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KorbakSCBBPBP23,
  author       = {Tomasz Korbak and
                  Kejian Shi and
                  Angelica Chen and
                  Rasika Vinayak Bhalerao and
                  Christopher L. Buckley and
                  Jason Phang and
                  Samuel R. Bowman and
                  Ethan Perez},
  editor       = {Andreas Krause and
                  Emma Brunskill and
                  Kyunghyun Cho and
                  Barbara Engelhardt and
                  Sivan Sabato and
                  Jonathan Scarlett},
  title        = {Pretraining Language Models with Human Preferences},
  booktitle    = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
                  2023, Honolulu, Hawaii, {USA}},
  series       = {Proceedings of Machine Learning Research},
  volume       = {202},
  pages        = {17506--17533},
  publisher    = {{PMLR}},
  year         = {2023},
  url          = {https://proceedings.mlr.press/v202/korbak23a.html},
  timestamp    = {Mon, 28 Aug 2023 17:23:08 +0200},
  biburl       = {https://dblp.org/rec/conf/icml/KorbakSCBBPBP23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PhangMHC23,
  author       = {Jason Phang and
                  Yi Mao and
                  Pengcheng He and
                  Weizhu Chen},
  editor       = {Andreas Krause and
                  Emma Brunskill and
                  Kyunghyun Cho and
                  Barbara Engelhardt and
                  Sivan Sabato and
                  Jonathan Scarlett},
  title        = {HyperTuning: Toward Adapting Large Language Models without Back-propagation},
  booktitle    = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
                  2023, Honolulu, Hawaii, {USA}},
  series       = {Proceedings of Machine Learning Research},
  volume       = {202},
  pages        = {27854--27875},
  publisher    = {{PMLR}},
  year         = {2023},
  url          = {https://proceedings.mlr.press/v202/phang23a.html},
  timestamp    = {Mon, 28 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icml/PhangMHC23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-08582,
  author       = {Tomasz Korbak and
                  Kejian Shi and
                  Angelica Chen and
                  Rasika Bhalerao and
                  Christopher L. Buckley and
                  Jason Phang and
                  Samuel R. Bowman and
                  Ethan Perez},
  title        = {Pretraining Language Models with Human Preferences},
  journal      = {CoRR},
  volume       = {abs/2302.08582},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2302.08582},
  doi          = {10.48550/ARXIV.2302.08582},
  eprinttype    = {arXiv},
  eprint       = {2302.08582},
  timestamp    = {Thu, 23 Feb 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2302-08582.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2304-08354,
  author       = {Yujia Qin and
                  Shengding Hu and
                  Yankai Lin and
                  Weize Chen and
                  Ning Ding and
                  Ganqu Cui and
                  Zheni Zeng and
                  Yufei Huang and
                  Chaojun Xiao and
                  Chi Han and
                  Yi Ren Fung and
                  Yusheng Su and
                  Huadong Wang and
                  Cheng Qian and
                  Runchu Tian and
                  Kunlun Zhu and
                  Shihao Liang and
                  Xingyu Shen and
                  Bokai Xu and
                  Zhen Zhang and
                  Yining Ye and
                  Bowen Li and
                  Ziwei Tang and
                  Jing Yi and
                  Yuzhang Zhu and
                  Zhenning Dai and
                  Lan Yan and
                  Xin Cong and
                  Yaxi Lu and
                  Weilin Zhao and
                  Yuxiang Huang and
                  Junxi Yan and
                  Xu Han and
                  Xian Sun and
                  Dahai Li and
                  Jason Phang and
                  Cheng Yang and
                  Tongshuang Wu and
                  Heng Ji and
                  Zhiyuan Liu and
                  Maosong Sun},
  title        = {Tool Learning with Foundation Models},
  journal      = {CoRR},
  volume       = {abs/2304.08354},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2304.08354},
  doi          = {10.48550/ARXIV.2304.08354},
  eprinttype    = {arXiv},
  eprint       = {2304.08354},
  timestamp    = {Wed, 20 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2304-08354.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-14279,
  author       = {Angelica Chen and
                  Jason Phang and
                  Alicia Parrish and
                  Vishakh Padmakumar and
                  Chen Zhao and
                  Samuel R. Bowman and
                  Kyunghyun Cho},
  title        = {Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs},
  journal      = {CoRR},
  volume       = {abs/2305.14279},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2305.14279},
  doi          = {10.48550/ARXIV.2305.14279},
  eprinttype    = {arXiv},
  eprint       = {2305.14279},
  timestamp    = {Mon, 05 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-14279.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-08963,
  author       = {Xiangru Tang and
                  Yiming Zong and
                  Jason Phang and
                  Yilun Zhao and
                  Wangchunshu Zhou and
                  Arman Cohan and
                  Mark Gerstein},
  title        = {Struc-Bench: Are Large Language Models Really Good at Generating Complex
                  Structured Data?},
  journal      = {CoRR},
  volume       = {abs/2309.08963},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2309.08963},
  doi          = {10.48550/ARXIV.2309.08963},
  eprinttype    = {arXiv},
  eprint       = {2309.08963},
  timestamp    = {Mon, 25 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-08963.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/ParrishCNPPTHB22,
  author       = {Alicia Parrish and
                  Angelica Chen and
                  Nikita Nangia and
                  Vishakh Padmakumar and
                  Jason Phang and
                  Jana Thompson and
                  Phu Mon Htut and
                  Samuel R. Bowman},
  editor       = {Smaranda Muresan and
                  Preslav Nakov and
                  Aline Villavicencio},
  title        = {{BBQ:} {A} hand-built bias benchmark for question answering},
  booktitle    = {Findings of the Association for Computational Linguistics: {ACL} 2022,
                  Dublin, Ireland, May 22-27, 2022},
  pages        = {2086--2105},
  publisher    = {Association for Computational Linguistics},
  year         = {2022},
  url          = {https://doi.org/10.18653/v1/2022.findings-acl.165},
  doi          = {10.18653/V1/2022.FINDINGS-ACL.165},
  timestamp    = {Mon, 01 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/acl/ParrishCNPPTHB22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/ScaoWHBBBEMPPRS22,
  author       = {Teven Le Scao and
                  Thomas Wang and
                  Daniel Hesslow and
                  Stas Bekman and
                  M. Saiful Bari and
                  Stella Biderman and
                  Hady Elsahar and
                  Niklas Muennighoff and
                  Jason Phang and
                  Ofir Press and
                  Colin Raffel and
                  Victor Sanh and
                  Sheng Shen and
                  Lintang Sutawika and
                  Jaesung Tae and
                  Zheng Xin Yong and
                  Julien Launay and
                  Iz Beltagy},
  editor       = {Yoav Goldberg and
                  Zornitsa Kozareva and
                  Yue Zhang},
  title        = {What Language Model to Train if You Have One Million {GPU} Hours?},
  booktitle    = {Findings of the Association for Computational Linguistics: {EMNLP}
                  2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
  pages        = {765--782},
  publisher    = {Association for Computational Linguistics},
  year         = {2022},
  url          = {https://doi.org/10.18653/v1/2022.findings-emnlp.54},
  doi          = {10.18653/V1/2022.FINDINGS-EMNLP.54},
  timestamp    = {Thu, 10 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/ScaoWHBBBEMPPRS22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/WangPCPB22,
  author       = {Alex Wang and
                  Richard Yuanzhe Pang and
                  Angelica Chen and
                  Jason Phang and
                  Samuel R. Bowman},
  editor       = {Yoav Goldberg and
                  Zornitsa Kozareva and
                  Yue Zhang},
  title        = {SQuALITY: Building a Long-Document Summarization Dataset the Hard
                  Way},
  booktitle    = {Proceedings of the 2022 Conference on Empirical Methods in Natural
                  Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates,
                  December 7-11, 2022},
  pages        = {1139--1156},
  publisher    = {Association for Computational Linguistics},
  year         = {2022},
  url          = {https://doi.org/10.18653/v1/2022.emnlp-main.75},
  doi          = {10.18653/V1/2022.EMNLP-MAIN.75},
  timestamp    = {Thu, 10 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/WangPCPB22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/PangPJNPCPMT0B22,
  author       = {Richard Yuanzhe Pang and
                  Alicia Parrish and
                  Nitish Joshi and
                  Nikita Nangia and
                  Jason Phang and
                  Angelica Chen and
                  Vishakh Padmakumar and
                  Johnny Ma and
                  Jana Thompson and
                  He He and
                  Samuel R. Bowman},
  editor       = {Marine Carpuat and
                  Marie{-}Catherine de Marneffe and
                  Iv{\'{a}}n Vladimir Meza Ru{\'{\i}}z},
  title        = {QuALITY: Question Answering with Long Input Texts, Yes!},
  booktitle    = {Proceedings of the 2022 Conference of the North American Chapter of
                  the Association for Computational Linguistics: Human Language Technologies,
                  {NAACL} 2022, Seattle, WA, United States, July 10-15, 2022},
  pages        = {5336--5358},
  publisher    = {Association for Computational Linguistics},
  year         = {2022},
  url          = {https://doi.org/10.18653/v1/2022.naacl-main.391},
  doi          = {10.18653/V1/2022.NAACL-MAIN.391},
  timestamp    = {Mon, 01 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/naacl/PangPJNPCPMT0B22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-05212,
  author       = {Alicia Parrish and
                  Harsh Trivedi and
                  Ethan Perez and
                  Angelica Chen and
                  Nikita Nangia and
                  Jason Phang and
                  Samuel R. Bowman},
  title        = {Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension
                  Questions},
  journal      = {CoRR},
  volume       = {abs/2204.05212},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2204.05212},
  doi          = {10.48550/ARXIV.2204.05212},
  eprinttype    = {arXiv},
  eprint       = {2204.05212},
  timestamp    = {Wed, 13 Apr 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2204-05212.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-06745,
  author       = {Sid Black and
                  Stella Biderman and
                  Eric Hallahan and
                  Quentin Anthony and
                  Leo Gao and
                  Laurence Golding and
                  Horace He and
                  Connor Leahy and
                  Kyle McDonell and
                  Jason Phang and
                  Michael Pieler and
                  USVSN Sai Prashanth and
                  Shivanshu Purohit and
                  Laria Reynolds and
                  Jonathan Tow and
                  Ben Wang and
                  Samuel Weinbach},
  title        = {GPT-NeoX-20B: An Open-Source Autoregressive Language Model},
  journal      = {CoRR},
  volume       = {abs/2204.06745},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2204.06745},
  doi          = {10.48550/ARXIV.2204.06745},
  eprinttype    = {arXiv},
  eprint       = {2204.06745},
  timestamp    = {Tue, 19 Apr 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2204-06745.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-11465,
  author       = {Alex Wang and
                  Richard Yuanzhe Pang and
                  Angelica Chen and
                  Jason Phang and
                  Samuel R. Bowman},
  title        = {SQuALITY: Building a Long-Document Summarization Dataset the Hard
                  Way},
  journal      = {CoRR},
  volume       = {abs/2205.11465},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2205.11465},
  doi          = {10.48550/ARXIV.2205.11465},
  eprinttype    = {arXiv},
  eprint       = {2205.11465},
  timestamp    = {Mon, 30 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2205-11465.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2208-04347,
  author       = {Jason Phang and
                  Yao Zhao and
                  Peter J. Liu},
  title        = {Investigating Efficiently Extending Transformers for Long Input Summarization},
  journal      = {CoRR},
  volume       = {abs/2208.04347},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2208.04347},
  doi          = {10.48550/ARXIV.2208.04347},
  eprinttype    = {arXiv},
  eprint       = {2208.04347},
  timestamp    = {Tue, 16 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2208-04347.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2208-12852,
  author       = {Julian Michael and
                  Ari Holtzman and
                  Alicia Parrish and
                  Aaron Mueller and
                  Alex Wang and
                  Angelica Chen and
                  Divyam Madaan and
                  Nikita Nangia and
                  Richard Yuanzhe Pang and
                  Jason Phang and
                  Samuel R. Bowman},
  title        = {What Do {NLP} Researchers Believe? Results of the {NLP} Community
                  Metasurvey},
  journal      = {CoRR},
  volume       = {abs/2208.12852},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2208.12852},
  doi          = {10.48550/ARXIV.2208.12852},
  eprinttype    = {arXiv},
  eprint       = {2208.12852},
  timestamp    = {Thu, 01 Sep 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2208-12852.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-06413,
  author       = {Jason Phang and
                  Herbie Bradley and
                  Leo Gao and
                  Louis Castricato and
                  Stella Biderman},
  title        = {EleutherAI: Going Beyond "Open Science" to "Science
                  in the Open"},
  journal      = {CoRR},
  volume       = {abs/2210.06413},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2210.06413},
  doi          = {10.48550/ARXIV.2210.06413},
  eprinttype    = {arXiv},
  eprint       = {2210.06413},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-06413.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-10860,
  author       = {Alicia Parrish and
                  Harsh Trivedi and
                  Nikita Nangia and
                  Vishakh Padmakumar and
                  Jason Phang and
                  Amanpreet Singh Saimbhi and
                  Samuel R. Bowman},
  title        = {Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension
                  Questions},
  journal      = {CoRR},
  volume       = {abs/2210.10860},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2210.10860},
  doi          = {10.48550/ARXIV.2210.10860},
  eprinttype    = {arXiv},
  eprint       = {2210.10860},
  timestamp    = {Tue, 25 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-10860.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-15424,
  author       = {Teven Le Scao and
                  Thomas Wang and
                  Daniel Hesslow and
                  Lucile Saulnier and
                  Stas Bekman and
                  M. Saiful Bari and
                  Stella Biderman and
                  Hady Elsahar and
                  Niklas Muennighoff and
                  Jason Phang and
                  Ofir Press and
                  Colin Raffel and
                  Victor Sanh and
                  Sheng Shen and
                  Lintang Sutawika and
                  Jaesung Tae and
                  Zheng Xin Yong and
                  Julien Launay and
                  Iz Beltagy},
  title        = {What Language Model to Train if You Have One Million {GPU} Hours?},
  journal      = {CoRR},
  volume       = {abs/2210.15424},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2210.15424},
  doi          = {10.48550/ARXIV.2210.15424},
  eprinttype    = {arXiv},
  eprint       = {2210.15424},
  timestamp    = {Wed, 02 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-15424.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-12485,
  author       = {Jason Phang and
                  Yi Mao and
                  Pengcheng He and
                  Weizhu Chen},
  title        = {HyperTuning: Toward Adapting Large Language Models without Back-propagation},
  journal      = {CoRR},
  volume       = {abs/2211.12485},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2211.12485},
  doi          = {10.48550/ARXIV.2211.12485},
  eprinttype    = {arXiv},
  eprint       = {2211.12485},
  timestamp    = {Thu, 24 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2211-12485.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jdi/WuHSPPMKCHMG21,
  author       = {Nan Wu and
                  Zhe Huang and
                  Yiqiu Shen and
                  Jungkyu Park and
                  Jason Phang and
                  Taro Makino and
                  Sungheon Gene Kim and
                  Kyunghyun Cho and
                  Laura Heacock and
                  Linda Moy and
                  Krzysztof J. Geras},
  title        = {Reducing False-Positive Biopsies using Deep Neural Networks that Utilize
                  both Local and Global Image Context of Screening Mammograms},
  journal      = {J. Digit. Imaging},
  volume       = {34},
  number       = {6},
  pages        = {1414--1423},
  year         = {2021},
  url          = {https://doi.org/10.1007/s10278-021-00530-6},
  doi          = {10.1007/S10278-021-00530-6},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/jdi/WuHSPPMKCHMG21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mia/ShenWPPLTHKMCG21,
  author       = {Yiqiu Shen and
                  Nan Wu and
                  Jason Phang and
                  Jungkyu Park and
                  Kangning Liu and
                  Sudarshini Tyagi and
                  Laura Heacock and
                  Sungheon Gene Kim and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  title        = {An interpretable classifier for high-resolution breast cancer screening
                  images utilizing weakly supervised localization},
  journal      = {Medical Image Anal.},
  volume       = {68},
  pages        = {101908},
  year         = {2021},
  url          = {https://doi.org/10.1016/j.media.2020.101908},
  doi          = {10.1016/J.MEDIA.2020.101908},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/mia/ShenWPPLTHKMCG21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/VaniaHHMPPLCB20,
  author       = {Clara Vania and
                  Phu Mon Htut and
                  William Huang and
                  Dhara A. Mungra and
                  Richard Yuanzhe Pang and
                  Jason Phang and
                  Haokun Liu and
                  Kyunghyun Cho and
                  Samuel R. Bowman},
  editor       = {Chengqing Zong and
                  Fei Xia and
                  Wenjie Li and
                  Roberto Navigli},
  title        = {Comparing Test Sets with Item Response Theory},
  booktitle    = {Proceedings of the 59th Annual Meeting of the Association for Computational
                  Linguistics and the 11th International Joint Conference on Natural
                  Language Processing, {ACL/IJCNLP} 2021, (Volume 1: Long Papers), Virtual
                  Event, August 1-6, 2021},
  pages        = {1141--1158},
  publisher    = {Association for Computational Linguistics},
  year         = {2021},
  url          = {https://doi.org/10.18653/v1/2021.acl-long.92},
  doi          = {10.18653/V1/2021.ACL-LONG.92},
  timestamp    = {Mon, 09 Aug 2021 16:25:37 +0200},
  biburl       = {https://dblp.org/rec/conf/acl/VaniaHHMPPLCB20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/blackboxnlp/PhangLB21,
  author       = {Jason Phang and
                  Haokun Liu and
                  Samuel R. Bowman},
  editor       = {Jasmijn Bastings and
                  Yonatan Belinkov and
                  Emmanuel Dupoux and
                  Mario Giulianelli and
                  Dieuwke Hupkes and
                  Yuval Pinter and
                  Hassan Sajjad},
  title        = {Fine-Tuned Transformers Show Clusters of Similar Representations Across
                  Layers},
  booktitle    = {Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting
                  Neural Networks for NLP, BlackboxNLP@EMNLP 2021, Punta Cana, Dominican
                  Republic, November 11, 2021},
  pages        = {529--538},
  publisher    = {Association for Computational Linguistics},
  year         = {2021},
  url          = {https://doi.org/10.18653/v1/2021.blackboxnlp-1.42},
  doi          = {10.18653/V1/2021.BLACKBOXNLP-1.42},
  timestamp    = {Fri, 15 Sep 2023 14:10:05 +0200},
  biburl       = {https://dblp.org/rec/conf/blackboxnlp/PhangLB21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-00027,
  author       = {Leo Gao and
                  Stella Biderman and
                  Sid Black and
                  Laurence Golding and
                  Travis Hoppe and
                  Charles Foster and
                  Jason Phang and
                  Horace He and
                  Anish Thite and
                  Noa Nabeshima and
                  Shawn Presser and
                  Connor Leahy},
  title        = {The Pile: An 800GB Dataset of Diverse Text for Language Modeling},
  journal      = {CoRR},
  volume       = {abs/2101.00027},
  year         = {2021},
  url          = {https://arxiv.org/abs/2101.00027},
  eprinttype    = {arXiv},
  eprint       = {2101.00027},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2101-00027.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-00840,
  author       = {Clara Vania and
                  Phu Mon Htut and
                  William Huang and
                  Dhara A. Mungra and
                  Richard Yuanzhe Pang and
                  Jason Phang and
                  Haokun Liu and
                  Kyunghyun Cho and
                  Samuel R. Bowman},
  title        = {Comparing Test Sets with Item Response Theory},
  journal      = {CoRR},
  volume       = {abs/2106.00840},
  year         = {2021},
  url          = {https://arxiv.org/abs/2106.00840},
  eprinttype    = {arXiv},
  eprint       = {2106.00840},
  timestamp    = {Wed, 09 Jun 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-00840.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-08406,
  author       = {Jason Phang and
                  Haokun Liu and
                  Samuel R. Bowman},
  title        = {Fine-Tuned Transformers Show Clusters of Similar Representations Across
                  Layers},
  journal      = {CoRR},
  volume       = {abs/2109.08406},
  year         = {2021},
  url          = {https://arxiv.org/abs/2109.08406},
  eprinttype    = {arXiv},
  eprint       = {2109.08406},
  timestamp    = {Wed, 22 Sep 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2109-08406.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-08193,
  author       = {Alicia Parrish and
                  Angelica Chen and
                  Nikita Nangia and
                  Vishakh Padmakumar and
                  Jason Phang and
                  Jana Thompson and
                  Phu Mon Htut and
                  Samuel R. Bowman},
  title        = {{BBQ:} {A} Hand-Built Bias Benchmark for Question Answering},
  journal      = {CoRR},
  volume       = {abs/2110.08193},
  year         = {2021},
  url          = {https://arxiv.org/abs/2110.08193},
  eprinttype    = {arXiv},
  eprint       = {2110.08193},
  timestamp    = {Fri, 22 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-08193.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-08181,
  author       = {Jason Phang and
                  Angelica Chen and
                  William Huang and
                  Samuel R. Bowman},
  title        = {Adversarially Constructed Evaluation Sets Are More Challenging, but
                  May Not Be Fair},
  journal      = {CoRR},
  volume       = {abs/2111.08181},
  year         = {2021},
  url          = {https://arxiv.org/abs/2111.08181},
  eprinttype    = {arXiv},
  eprint       = {2111.08181},
  timestamp    = {Mon, 22 Nov 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2111-08181.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-08608,
  author       = {Richard Yuanzhe Pang and
                  Alicia Parrish and
                  Nitish Joshi and
                  Nikita Nangia and
                  Jason Phang and
                  Angelica Chen and
                  Vishakh Padmakumar and
                  Johnny Ma and
                  Jana Thompson and
                  He He and
                  Samuel R. Bowman},
  title        = {QuALITY: Question Answering with Long Input Texts, Yes!},
  journal      = {CoRR},
  volume       = {abs/2112.08608},
  year         = {2021},
  url          = {https://arxiv.org/abs/2112.08608},
  eprinttype    = {arXiv},
  eprint       = {2112.08608},
  timestamp    = {Tue, 04 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2112-08608.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmi/WuPPSHZJFKKWPGL20,
  author       = {Nan Wu and
                  Jason Phang and
                  Jungkyu Park and
                  Yiqiu Shen and
                  Zhe Huang and
                  Masha Zorin and
                  Stanislaw Jastrzebski and
                  Thibault F{\'{e}}vry and
                  Joe Katsnelson and
                  Eric Kim and
                  Stacey Wolfson and
                  Ujas Parikh and
                  Sushma Gaddam and
                  Leng Leng Young Lin and
                  Kara Ho and
                  Joshua D. Weinstein and
                  Beatriu Reig and
                  Yiming Gao and
                  Hildegard Toth and
                  Kristine Pysarenko and
                  Alana Lewin and
                  Jiyon Lee and
                  Krystal Airola and
                  Eralda Mema and
                  Stephanie Chung and
                  Esther Hwang and
                  Naziya Samreen and
                  Sungheon Gene Kim and
                  Laura Heacock and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  title        = {Deep Neural Networks Improve Radiologists' Performance in Breast Cancer
                  Screening},
  journal      = {{IEEE} Trans. Medical Imaging},
  volume       = {39},
  number       = {4},
  pages        = {1184--1194},
  year         = {2020},
  url          = {https://doi.org/10.1109/TMI.2019.2945514},
  doi          = {10.1109/TMI.2019.2945514},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tmi/WuPPSHZJFKKWPGL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/PruksachatkunYL20,
  author       = {Yada Pruksachatkun and
                  Philip Yeres and
                  Haokun Liu and
                  Jason Phang and
                  Phu Mon Htut and
                  Alex Wang and
                  Ian Tenney and
                  Samuel R. Bowman},
  editor       = {Asli Celikyilmaz and
                  Tsung{-}Hsien Wen},
  title        = {jiant: {A} Software Toolkit for Research on General-Purpose Text Understanding
                  Models},
  booktitle    = {Proceedings of the 58th Annual Meeting of the Association for Computational
                  Linguistics: System Demonstrations, {ACL} 2020, Online, July 5-10,
                  2020},
  pages        = {109--117},
  publisher    = {Association for Computational Linguistics},
  year         = {2020},
  url          = {https://doi.org/10.18653/v1/2020.acl-demos.15},
  doi          = {10.18653/V1/2020.ACL-DEMOS.15},
  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/acl/PruksachatkunYL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/PruksachatkunPL20,
  author       = {Yada Pruksachatkun and
                  Jason Phang and
                  Haokun Liu and
                  Phu Mon Htut and
                  Xiaoyi Zhang and
                  Richard Yuanzhe Pang and
                  Clara Vania and
                  Katharina Kann and
                  Samuel R. Bowman},
  editor       = {Dan Jurafsky and
                  Joyce Chai and
                  Natalie Schluter and
                  Joel R. Tetreault},
  title        = {Intermediate-Task Transfer Learning with Pretrained Language Models:
                  When and Why Does It Work?},
  booktitle    = {Proceedings of the 58th Annual Meeting of the Association for Computational
                  Linguistics, {ACL} 2020, Online, July 5-10, 2020},
  pages        = {5231--5247},
  publisher    = {Association for Computational Linguistics},
  year         = {2020},
  url          = {https://doi.org/10.18653/v1/2020.acl-main.467},
  doi          = {10.18653/V1/2020.ACL-MAIN.467},
  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/acl/PruksachatkunPL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnlp/PhangCHPLVKB20,
  author       = {Jason Phang and
                  Iacer Calixto and
                  Phu Mon Htut and
                  Yada Pruksachatkun and
                  Haokun Liu and
                  Clara Vania and
                  Katharina Kann and
                  Samuel R. Bowman},
  editor       = {Kam{-}Fai Wong and
                  Kevin Knight and
                  Hua Wu},
  title        = {English Intermediate-Task Training Improves Zero-Shot Cross-Lingual
                  Transfer Too},
  booktitle    = {Proceedings of the 1st Conference of the Asia-Pacific Chapter of the
                  Association for Computational Linguistics and the 10th International
                  Joint Conference on Natural Language Processing, {AACL/IJCNLP} 2020,
                  Suzhou, China, December 4-7, 2020},
  pages        = {557--575},
  publisher    = {Association for Computational Linguistics},
  year         = {2020},
  url          = {https://aclanthology.org/2020.aacl-main.56/},
  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ijcnlp/PhangCHPLVKB20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-07613,
  author       = {Yiqiu Shen and
                  Nan Wu and
                  Jason Phang and
                  Jungkyu Park and
                  Kangning Liu and
                  Sudarshini Tyagi and
                  Laura Heacock and
                  Sungheon Gene Kim and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  title        = {An interpretable classifier for high-resolution breast cancer screening
                  images utilizing weakly supervised localization},
  journal      = {CoRR},
  volume       = {abs/2002.07613},
  year         = {2020},
  url          = {https://arxiv.org/abs/2002.07613},
  eprinttype    = {arXiv},
  eprint       = {2002.07613},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2002-07613.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-02249,
  author       = {Yada Pruksachatkun and
                  Philip Yeres and
                  Haokun Liu and
                  Jason Phang and
                  Phu Mon Htut and
                  Alex Wang and
                  Ian Tenney and
                  Samuel R. Bowman},
  title        = {jiant: {A} Software Toolkit for Research on General-Purpose Text Understanding
                  Models},
  journal      = {CoRR},
  volume       = {abs/2003.02249},
  year         = {2020},
  url          = {https://arxiv.org/abs/2003.02249},
  eprinttype    = {arXiv},
  eprint       = {2003.02249},
  timestamp    = {Thu, 25 Jun 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2003-02249.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-00628,
  author       = {Yada Pruksachatkun and
                  Jason Phang and
                  Haokun Liu and
                  Phu Mon Htut and
                  Xiaoyi Zhang and
                  Richard Yuanzhe Pang and
                  Clara Vania and
                  Katharina Kann and
                  Samuel R. Bowman},
  title        = {Intermediate-Task Transfer Learning with Pretrained Models for Natural
                  Language Understanding: When and Why Does It Work?},
  journal      = {CoRR},
  volume       = {abs/2005.00628},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.00628},
  eprinttype    = {arXiv},
  eprint       = {2005.00628},
  timestamp    = {Fri, 08 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-00628.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-13013,
  author       = {Jason Phang and
                  Phu Mon Htut and
                  Yada Pruksachatkun and
                  Haokun Liu and
                  Clara Vania and
                  Katharina Kann and
                  Iacer Calixto and
                  Samuel R. Bowman},
  title        = {English Intermediate-Task Training Improves Zero-Shot Cross-Lingual
                  Transfer Too},
  journal      = {CoRR},
  volume       = {abs/2005.13013},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.13013},
  eprinttype    = {arXiv},
  eprint       = {2005.13013},
  timestamp    = {Thu, 28 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-13013.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-09282,
  author       = {Nan Wu and
                  Zhe Huang and
                  Yiqiu Shen and
                  Jungkyu Park and
                  Jason Phang and
                  Taro Makino and
                  Sungheon Gene Kim and
                  Kyunghyun Cho and
                  Laura Heacock and
                  Linda Moy and
                  Krzysztof J. Geras},
  title        = {Reducing false-positive biopsies with deep neural networks that utilize
                  local and global information in screening mammograms},
  journal      = {CoRR},
  volume       = {abs/2009.09282},
  year         = {2020},
  url          = {https://arxiv.org/abs/2009.09282},
  eprinttype    = {arXiv},
  eprint       = {2009.09282},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2009-09282.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-09750,
  author       = {Jason Phang and
                  Jungkyu Park and
                  Krzysztof J. Geras},
  title        = {Investigating and Simplifying Masking-based Saliency Methods for Model
                  Interpretability},
  journal      = {CoRR},
  volume       = {abs/2010.09750},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.09750},
  eprinttype    = {arXiv},
  eprint       = {2010.09750},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-09750.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/WarstadtCGPBNAB19,
  author       = {Alex Warstadt and
                  Yu Cao and
                  Ioana Grosu and
                  Wei Peng and
                  Hagen Blix and
                  Yining Nie and
                  Anna Alsop and
                  Shikha Bordia and
                  Haokun Liu and
                  Alicia Parrish and
                  Sheng{-}Fu Wang and
                  Jason Phang and
                  Anhad Mohananey and
                  Phu Mon Htut and
                  Paloma Jeretic and
                  Samuel R. Bowman},
  editor       = {Kentaro Inui and
                  Jing Jiang and
                  Vincent Ng and
                  Xiaojun Wan},
  title        = {Investigating BERT's Knowledge of Language: Five Analysis Methods
                  with NPIs},
  booktitle    = {Proceedings of the 2019 Conference on Empirical Methods in Natural
                  Language Processing and the 9th International Joint Conference on
                  Natural Language Processing, {EMNLP-IJCNLP} 2019, Hong Kong, China,
                  November 3-7, 2019},
  pages        = {2877--2887},
  publisher    = {Association for Computational Linguistics},
  year         = {2019},
  url          = {https://doi.org/10.18653/v1/D19-1286},
  doi          = {10.18653/V1/D19-1286},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/WarstadtCGPBNAB19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/miccai/ShenWPPKMCG19,
  author       = {Yiqiu Shen and
                  Nan Wu and
                  Jason Phang and
                  Jungkyu Park and
                  Sungheon Gene Kim and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  editor       = {Heung{-}Il Suk and
                  Mingxia Liu and
                  Pingkun Yan and
                  Chunfeng Lian},
  title        = {Globally-Aware Multiple Instance Classifier for Breast Cancer Screening},
  booktitle    = {Machine Learning in Medical Imaging - 10th International Workshop,
                  {MLMI} 2019, Held in Conjunction with {MICCAI} 2019, Shenzhen, China,
                  October 13, 2019, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {11861},
  pages        = {18--26},
  publisher    = {Springer},
  year         = {2019},
  url          = {https://doi.org/10.1007/978-3-030-32692-0\_3},
  doi          = {10.1007/978-3-030-32692-0\_3},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/miccai/ShenWPPKMCG19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-08297,
  author       = {Nan Wu and
                  Jason Phang and
                  Jungkyu Park and
                  Yiqiu Shen and
                  Zhe Huang and
                  Masha Zorin and
                  Stanislaw Jastrzebski and
                  Thibault F{\'{e}}vry and
                  Joe Katsnelson and
                  Eric Kim and
                  Stacey Wolfson and
                  Ujas Parikh and
                  Sushma Gaddam and
                  Leng Leng Young Lin and
                  Kara Ho and
                  Joshua D. Weinstein and
                  Beatriu Reig and
                  Yiming Gao and
                  Hildegard Toth and
                  Kristine Pysarenko and
                  Alana Lewin and
                  Jiyon Lee and
                  Krystal Airola and
                  Eralda Mema and
                  Stephanie Chung and
                  Esther Hwang and
                  Naziya Samreen and
                  Sungheon Gene Kim and
                  Laura Heacock and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  title        = {Deep Neural Networks Improve Radiologists' Performance in Breast Cancer
                  Screening},
  journal      = {CoRR},
  volume       = {abs/1903.08297},
  year         = {2019},
  url          = {http://arxiv.org/abs/1903.08297},
  eprinttype    = {arXiv},
  eprint       = {1903.08297},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1903-08297.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-02846,
  author       = {Yiqiu Shen and
                  Nan Wu and
                  Jason Phang and
                  Jungkyu Park and
                  Sungheon Gene Kim and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  title        = {Globally-Aware Multiple Instance Classifier for Breast Cancer Screening},
  journal      = {CoRR},
  volume       = {abs/1906.02846},
  year         = {2019},
  url          = {http://arxiv.org/abs/1906.02846},
  eprinttype    = {arXiv},
  eprint       = {1906.02846},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1906-02846.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-13057,
  author       = {Jungkyu Park and
                  Jason Phang and
                  Yiqiu Shen and
                  Nan Wu and
                  Sungheon Gene Kim and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  title        = {Screening Mammogram Classification with Prior Exams},
  journal      = {CoRR},
  volume       = {abs/1907.13057},
  year         = {2019},
  url          = {http://arxiv.org/abs/1907.13057},
  eprinttype    = {arXiv},
  eprint       = {1907.13057},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1907-13057.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-00615,
  author       = {Thibault F{\'{e}}vry and
                  Jason Phang and
                  Nan Wu and
                  Sungheon Gene Kim and
                  Linda Moy and
                  Kyunghyun Cho and
                  Krzysztof J. Geras},
  title        = {Improving localization-based approaches for breast cancer screening
                  exam classification},
  journal      = {CoRR},
  volume       = {abs/1908.00615},
  year         = {2019},
  url          = {http://arxiv.org/abs/1908.00615},
  eprinttype    = {arXiv},
  eprint       = {1908.00615},
  timestamp    = {Thu, 24 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1908-00615.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-02597,
  author       = {Alex Warstadt and
                  Yu Cao and
                  Ioana Grosu and
                  Wei Peng and
                  Hagen Blix and
                  Yining Nie and
                  Anna Alsop and
                  Shikha Bordia and
                  Haokun Liu and
                  Alicia Parrish and
                  Sheng{-}Fu Wang and
                  Jason Phang and
                  Anhad Mohananey and
                  Phu Mon Htut and
                  Paloma Jeretic and
                  Samuel R. Bowman},
  title        = {Investigating BERT's Knowledge of Language: Five Analysis Methods
                  with NPIs},
  journal      = {CoRR},
  volume       = {abs/1909.02597},
  year         = {2019},
  url          = {http://arxiv.org/abs/1909.02597},
  eprinttype    = {arXiv},
  eprint       = {1909.02597},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1909-02597.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-12246,
  author       = {Phu Mon Htut and
                  Jason Phang and
                  Shikha Bordia and
                  Samuel R. Bowman},
  title        = {Do Attention Heads in {BERT} Track Syntactic Dependencies?},
  journal      = {CoRR},
  volume       = {abs/1911.12246},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.12246},
  eprinttype    = {arXiv},
  eprint       = {1911.12246},
  timestamp    = {Tue, 03 Dec 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-12246.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/conll/FevryP18,
  author       = {Thibault F{\'{e}}vry and
                  Jason Phang},
  editor       = {Anna Korhonen and
                  Ivan Titov},
  title        = {Unsupervised Sentence Compression using Denoising Auto-Encoders},
  booktitle    = {Proceedings of the 22nd Conference on Computational Natural Language
                  Learning, CoNLL 2018, Brussels, Belgium, October 31 - November 1,
                  2018},
  pages        = {413--422},
  publisher    = {Association for Computational Linguistics},
  year         = {2018},
  url          = {https://doi.org/10.18653/v1/k18-1040},
  doi          = {10.18653/V1/K18-1040},
  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/conll/FevryP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-02669,
  author       = {Thibault F{\'{e}}vry and
                  Jason Phang},
  title        = {Unsupervised Sentence Compression using Denoising Auto-Encoders},
  journal      = {CoRR},
  volume       = {abs/1809.02669},
  year         = {2018},
  url          = {http://arxiv.org/abs/1809.02669},
  eprinttype    = {arXiv},
  eprint       = {1809.02669},
  timestamp    = {Fri, 05 Oct 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1809-02669.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-01088,
  author       = {Jason Phang and
                  Thibault F{\'{e}}vry and
                  Samuel R. Bowman},
  title        = {Sentence Encoders on STILTs: Supplementary Training on Intermediate
                  Labeled-data Tasks},
  journal      = {CoRR},
  volume       = {abs/1811.01088},
  year         = {2018},
  url          = {http://arxiv.org/abs/1811.01088},
  eprinttype    = {arXiv},
  eprint       = {1811.01088},
  timestamp    = {Thu, 22 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1811-01088.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics