Share this page:

Sequentially Controlled Text Generation

Alexander Spangher, Yao Ming, Xinyu Hua, and Nanyun Peng, in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.

Abstract


Bib Entry

@inproceedings{spangher2022sequentially,
  title = {Sequentially Controlled Text Generation},
  author = {Spangher, Alexander and Ming, Yao and Hua, Xinyu and Peng, Nanyun},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2022}
}

Related Publications

  • Sequentially Controlled Text Generation

    Alexander Spangher, Yao Ming, Xinyu Hua, and Nanyun Peng, in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.
    BibTeX Details
    @inproceedings{spangher2022sequentially,
      title = {Sequentially Controlled Text Generation},
      author = {Spangher, Alexander and Ming, Yao and Hua, Xinyu and Peng, Nanyun},
      booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
      year = {2022}
    }
    
    Details
  • AESOP: Paraphrase Generation with Adaptive Syntactic Control

    Jiao Sun, Xuezhe Ma, and Nanyun Peng, in The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
    Full Text Code Abstract BibTeX Details
    We propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases. Our model, AESOP, leverages a pretrained language model and adds deliberately chosen syntactical control via a retrieval-based selection module to generate fluent paraphrases. Experiments show that AESOP achieves state-of-the-art performances on semantic preservation and syntactic conformation on two benchmark datasets with ground-truth syntactic control from human-annotated exemplars. Moreover, with the retrieval-based target syntax selection module, AESOP generates paraphrases with even better qualities than the current best model using human-annotated target syntactic parses according to human evaluation. We further demonstrate the effectiveness of AESOP to improve classification models’ robustness to syntactic perturbation by data augmentation on two GLUE tasks.
    @inproceedings{sun2021aesop,
      title = {AESOP: Paraphrase Generation with Adaptive Syntactic Control},
      author = {Sun, Jiao and Ma, Xuezhe and Peng, Nanyun},
      booktitle = {The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
      year = {2021}
    }
    
    Details