Papers

google scholar, download bibtex

2023

• Coder reviewer reranking for code generation.
  Tianyi Zhang, Tao Yu, Tatsunori B Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, Sida I. Wang.
  International Conference on Machine Learning (ICML), 2023.
  

  @inproceedings{zhang2023coder,
    author = {T. Zhang and T. Yu and T. B. Hashimoto and M. Lewis and W. Yih and D. Fried and S. I. Wang},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {Coder Reviewer Reranking for Code Generation},
    year = {2023},
  }
  

  bib paper
  
  
• LEVER: learning to verify language-to-code generation with execution.
  Ansong Ni, Srini Iyer, Dragomir Radev, Ves Stoyanov, Wen-tau Yih, Sida I. Wang, Xi Victoria Lin.
  International Conference on Machine Learning (ICML), 2023.
  

  @inproceedings{ni2023lever,
    author = {A. Ni and S. Iyer and D. Radev and V. Stoyanov and W. Yih and S. I. Wang and X. V. Lin},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {LEVER: Learning to Verify Language-to-Code Generation with Execution},
    year = {2023},
  }
  

  bib paper
  
  
• DS-1000: a natural and reliable benchmark for data science code generation.
  Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Scott Wen-tau Yih, Daniel Fried, Sida Wang, Tao Yu.
  International Conference on Machine Learning (ICML), 2023.
  

  @inproceedings{lai2023ds1000,
    author = {Y. Lai and C. Li and Y. Wang and T. Zhang and R. Zhong and L. Zettlemoyer and S. W. Yih and D. Fried and S. Wang and T. Yu},
    booktitle = {International Conference on Machine Learning (ICML)},
    title = {D{S}-1000: A Natural and Reliable Benchmark for Data Science Code Generation},
    year = {2023},
  }
  

  bib paper
  
  
• InCoder: a generative model for code infilling and synthesis.
  Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer, Mike Lewis.
  International Conference on Learning Representations (ICLR), 2023.
  

  @inproceedings{fried2023incoder,
    author = {D. Fried and A. Aghajanyan and J. Lin and S. Wang and E. Wallace and F. Shi and R. Zhong and W. Yih and L. Zettlemoyer and M. Lewis},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {InCoder: A Generative Model for Code Infilling and Synthesis},
    year = {2023},
  }
  

  bib paper
  
  

2022

• Natural language to code translation with execution.
  Freda Shi, Daniel Fried, Marjan Ghazvininejad, Luke Zettlemoyer, Sida I. Wang.
  Empirical Methods in Natural Language Processing (EMNLP), 2022.
  

  @inproceedings{shi2022natural,
    author = {F. Shi and D. Fried and M. Ghazvininejad and L. Zettlemoyer and S. I. Wang},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Natural language to code translation with execution},
    year = {2022},
  }
  

  bib paper
  
  
• BitextEdit: automatic bitext editing for improved low-resource machine translation.
  Eleftheria Briakou, Sida I. Wang, Luke Zettlemoyer, Marjan Ghazvininejad.
  North American Association for Computational Linguistics (NAACL), 2022.
  

  @inproceedings{briakou2022bitextedit,
    author = {E. Briakou and S. I. Wang and L. Zettlemoyer and M. Ghazvininejad},
    booktitle = {North American Association for Computational Linguistics (NAACL)},
    title = {Bitext{E}dit: Automatic Bitext Editing for Improved Low-Resource Machine Translation},
    year = {2022},
  }
  

  bib paper
  
  
• On continual model refinement in out-of-distribution data streams.
  Bill Yuchen Lin, Sida Wang, Xi Victoria Lin, Robin Jia, Lin Xiao, Xiang Ren, Wen-tau Yih.
  Association for Computational Linguistics (ACL), 2022.
  

  @inproceedings{lin2022cmr,
    author = {B. Y. Lin and S. Wang and X. V. Lin and R. Jia and L. Xiao and X. Ren and W. Yih},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {On Continual Model Refinement in Out-of-Distribution Data Streams},
    year = {2022},
  }
  

  bib
  
  

2021

• SILG: the multi-domain symbolic interactive language grounding benchmark.
  Victor Zhong, Austin W. Hanjie, Sida Wang, Karthik Narasimhan, Luke Zettlemoyer.
  Advances in Neural Information Processing Systems (NeurIPS), 2021.
  

  @inproceedings{zhong2021silg,
    author = {V. Zhong and A. W. Hanjie and S. Wang and K. Narasimhan and L. Zettlemoyer},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark},
    year = {2021},
  }
  

  bib paper
  
  
• Bilingual lexicon induction via unsupervised bitext construction and word alignment.
  Haoyue Shi, Luke Zettlemoyer, Sida I. Wang.
  Association for Computational Linguistics (ACL), 2021.
  

  @inproceedings{shi2021lexicon,
    author = {H. Shi and L. Zettlemoyer and S. I. Wang},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment},
    year = {2021},
  }
  

  bib paper
  
  

2020

• Grounded adaptation for zero-shot executable semantic parsing.
  Victor Zhong, Mike Lewis, Sida I. Wang, Luke Zettlemoyer.
  Empirical Methods in Natural Language Processing (EMNLP), 2020.
  

  @inproceedings{zhong2020grounded,
    author = {V. Zhong and M. Lewis and S. I. Wang and L. Zettlemoyer},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Grounded adaptation for zero-shot executable semantic parsing},
    year = {2020},
  }
  

  bib paper code
  
  
• Pre-training via paraphrasing.
  Mike Lewis, Marjan Ghazvininejad, Gargi Ghosh, Armen Aghajanyan, Sida I. Wang, Luke Zettlemoyer.
  Advances in Neural Information Processing Systems (NeurIPS), 2020.
  

  @inproceedings{lewis2020pretrainpara,
    author = {M. Lewis and M. Ghazvininejad and G. Ghosh and A. Aghajanyan and S. I. Wang and L. Zettlemoyer},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Pre-training via paraphrasing},
    year = {2020},
  }
  

  bib paper
  
  

2019

• Interactive classification by asking informative questions.
  Lili Yu, Howard Chen, Sida I. Wang, Yoav Artzi, Tao Lei.
  Association for Computational Linguistics (ACL), 2019.
  

  @inproceedings{yu2019interactive,
    author = {L. Yu and H. Chen and S. I. Wang and Y. Artzi and T. Lei},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Interactive Classification by Asking Informative Questions},
    year = {2019},
  }
  

  bib paper
  
  

2018

• Simple recurrent units for highly parallelizable recurrence.
  Tao Lei, Yu Zhang, Sida I. Wang, Hui Dai, Yoav Artzi.
  Empirical Methods in Natural Language Processing (EMNLP), 2018.
  

  @inproceedings{tao2018sru,
    author = {T. Lei and Y. Zhang and S. I. Wang and H. Dai and Y. Artzi},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Simple Recurrent Units for Highly Parallelizable Recurrence},
    year = {2018},
  }
  

  bib paper code
  
  

2017

• Learning adaptive language interfaces through interaction.
  Sida I. Wang.
  Stanford University, 2017.
  

  @phdthesis{sidaw2017thesis,
    author = {S. I. Wang},
    school = {Stanford University},
    title = {Learning adaptive language interfaces through interaction},
    year = {2017},
  }
  

  bib paper project
  
  
• Naturalizing a programming language via interactive learning.
  Sida I. Wang, Samuel Ginn, Percy Liang, Christopher D Manning.
  Association for Computational Linguistics (ACL), 2017.
  

  @inproceedings{wang2017naturalizing,
    author = {S. I. Wang and S. Ginn and P. Liang and C. D. Manning},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Naturalizing a Programming Language via Interactive Learning},
    year = {2017},
  }
  

  bib paper slides project codalab
  
  
• Data noising as smoothing in neural network language models.
  Ziang Xie, Sida I. Wang, Jiwei Li, Daniel Lévy, Aiming Nie, Dan Jurafsky, Andrew Y. Ng.
  International Conference on Learning Representations (ICLR), 2017.
  

  @inproceedings{xie2017noising,
    author = {Z. Xie and S. I. Wang and J. Li and D. Lévy and A. Nie and D. Jurafsky and A. Y. Ng},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {Data Noising as Smoothing in Neural Network Language Models},
    year = {2017},
  }
  

  bib paper
  
  

2016

• Learning language games through interaction.
  Sida I. Wang, Percy Liang, Chris Manning.
  Association for Computational Linguistics (ACL), 2016. outstanding paper
  

  @inproceedings{wang2016games,
    author = {S. I. Wang and P. Liang and C. Manning},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Learning Language Games through Interaction},
    year = {2016},
  }
  

  bib paper slides project codalab
  
  

2015

• Estimating mixture models via mixture of polynomials.
  Sida I. Wang, Arun Chaganty, Percy Liang.
  Advances in Neural Information Processing Systems (NIPS), 2015.
  

  @inproceedings{wang2015polynomial,
    author = {S. I. Wang and A. Chaganty and P. Liang},
    booktitle = {Advances in Neural Information Processing Systems (NIPS)},
    title = {Estimating Mixture Models via Mixture of Polynomials},
    year = {2015},
  }
  

  bib paper poster code codalab
  
  

2014

• A sub-constant improvement in approximating the positive semidefinite Grothendieck problem.
  Roy Frostig, Sida I. Wang.
  arXiv preprint arXiv:1408.2270, 2014.
  

  @article{frostig2014subconstant,
    author = {R. Frostig and S. I. Wang},
    journal = {arXiv preprint arXiv:1408.2270},
    title = {A sub-constant improvement in approximating the positive semidefinite {G}rothendieck problem},
    year = {2014},
  }
  

  bib paper
  
  
• Altitude training: strong bounds for single-layer dropout.
  Stefan Wager, Will Fithian, Sida I. Wang, Percy Liang.
  Advances in Neural Information Processing Systems (NIPS), 2014.
  

  @inproceedings{wager2014altitude,
    author = {S. Wager and W. Fithian and S. I. Wang and P. Liang},
    booktitle = {Advances in Neural Information Processing Systems (NIPS)},
    title = {Altitude Training: Strong Bounds for Single-Layer Dropout},
    year = {2014},
  }
  

  bib paper
  
  
• Simple MAP inference via low-rank relaxations.
  Roy Frostig, Sida I. Wang, Percy Liang, Christopher D. Manning.
  Advances in Neural Information Processing Systems (NIPS), 2014.
  

  @inproceedings{frostig2014lowrank,
    author = {R. Frostig and S. I. Wang and P. Liang and C. D. Manning},
    booktitle = {Advances in Neural Information Processing Systems (NIPS)},
    title = {Simple {MAP} inference via low-rank relaxations},
    year = {2014},
  }
  

  bib paper codalab
  
  
• Relaxations for inference in restricted Boltzmann machines.
  Sida I. Wang, Roy Frostig, Percy Liang, Christopher D. Manning.
  International Conference on Learning Representations Workshop (ICLR), 2014.
  

  @inproceedings{wang2014iqp,
    author = {S. I. Wang and R. Frostig and P. Liang and C. D. Manning},
    booktitle = {International Conference on Learning Representations Workshop (ICLR)},
    title = {Relaxations for inference in restricted {B}oltzmann machines},
    year = {2014},
  }
  

  bib paper slides talk
  
  
• Human effort and machine learnability in computer aided translation.
  Spence Green, Sida I. Wang, Jason Chuang, Jeffrey Heer, and Christopher D. Manning.
  Empirical Methods in Natural Language Processing (EMNLP), 2014.
  

  @inproceedings{green14humaneffort,
    author = {S. Green and S. I. Wang and J. Chuang and J. Heer and and C. D. Manning},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Human Effort and Machine Learnability in Computer Aided Translation},
    year = {2014},
  }
  

  bib paper
  
  

2013

• Fast dropout training.
  Sida I. Wang, Christopher D. Manning.
  International Conference on Machine Learning (ICML), 2013.
  

  @inproceedings{wang2013fast,
    author = {S. I. Wang and C. D. Manning},
    booktitle = {International Conference on Machine Learning (ICML)},
    pages = {118--126},
    title = {Fast dropout training},
    year = {2013},
  }
  

  bib paper slides talk code
  
  
• Feature noising for log-linear structured prediction.
  Sida I. Wang, Mengqiu Wang, Stefan Wager, Percy Liang, Chris Manning.
  Empirical Methods in Natural Language Processing (EMNLP), 2013.
  

  @inproceedings{wang2013noising,
    author = {S. I. Wang and M. Wang and S. Wager and P. Liang and C. Manning},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    title = {Feature Noising for Log-linear Structured Prediction},
    year = {2013},
  }
  

  bib paper slides
  
  
• Dropout training as adaptive regularization.
  Stefan Wager, Sida I. Wang, Percy Liang.
  Advances in Neural Information Processing Systems (NIPS), 2013.
  

  @inproceedings{wager2013dropout,
    author = {S. Wager and S. I. Wang and P. Liang},
    booktitle = {Advances in Neural Information Processing Systems (NIPS)},
    title = {Dropout Training as Adaptive Regularization},
    year = {2013},
  }
  

  bib paper slides poster code
  
  
• Fast and adaptive online training of feature-rich translation models.
  Spence Green, Sida I. Wang, Dan Cer, Christopher D. Manning.
  Association for Computational Linguistics (ACL), 2013.
  

  @inproceedings{green2013feature,
    author = {S. Green and S. I. Wang and D. Cer and C. D. Manning},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Fast and Adaptive Online Training of Feature-Rich Translation Models},
    year = {2013},
  }
  

  bib paper slides
  
  
• Feature-rich phrase-based translation: Stanford University’s submission to the WMT 2013 translation task.
  Spence Green, Daniel Cer, Kevin Reschke, Rob Voigt, John Bauer, Sida I. Wang, Natalia Silveira, Julia Neidert, Christopher D. Manning.
  ACL 2013 Eighth Workshop on Statistical Machine Translation, 2013.
  

  @inproceedings{green2013wmt,
    author = {S. Green and D. Cer and K. Reschke and R. Voigt and J. Bauer and S. I. Wang and N. Silveira and J. Neidert and C. D. Manning},
    booktitle = {ACL 2013 Eighth Workshop on Statistical Machine Translation},
    title = {Feature-Rich Phrase-based Translation: {S}tanford {U}niversity’s Submission to the {WMT} 2013 Translation Task},
    year = {2013},
  }
  

  bib paper
  
  

2012

• Baselines and bigrams: simple, good sentiment and text classification.
  Sida I. Wang, Chris Manning.
  Association for Computational Linguistics (ACL), 2012.
  

  @inproceedings{wang2012simple,
    author = {S. I. Wang and C. Manning},
    booktitle = {Association for Computational Linguistics (ACL)},
    title = {Baselines and Bigrams: Simple, Good Sentiment and Text Classification},
    year = {2012},
  }
  

  bib paper code
  
  

2011

• Object recognition using capsules.
  Geoffrey E. Hinton, Alex Krizhevsky, Sida I. Wang.
  International Conference on Artificial Neural Networks (ICANN), 2011.
  

  @inproceedings{hinton2011transforming,
    author = {G. E. Hinton and A. Krizhevsky and S. I. Wang},
    booktitle = {International Conference on Artificial Neural Networks (ICANN)},
    title = {Object Recognition using Capsules},
    year = {2011},
  }
  

  bib paper
  
  
• Learning to extract parameterized features by predicting transformed images.
  Sida I. Wang.
  University of Toronto, 2011.
  

  @mastersthesis{wang2011trans,
    author = {S. I. Wang},
    school = {University of Toronto},
    title = {Learning to Extract Parameterized Features by Predicting Transformed Images},
    year = {2011},
  }
  

  bib paper