SAPPHIRE

Sapphire: enfoques para una generación mejorada de concepto a texto

Código para Sapphire: enfoques para la generación mejorada de concepto a texto publicado en INLG 2021 (mejor documento largo). Puedes citarlo de la siguiente manera:

 @inproceedings{feng-etal-2021-sapphire,
    title = "{SAPPHIRE}: Approaches for Enhanced Concept-to-Text Generation",
    author = "Feng, Steven Y.  and
      Huynh, Jessica  and
      Narisetty, Chaitanya Prasad  and
      Hovy, Eduard  and
      Gangal, Varun",
    booktitle = "Proceedings of the 14th International Conference on Natural Language Generation",
    month = aug,
    year = "2021",
    address = "Aberdeen, Scotland, UK",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.inlg-1.21",
    pages = "212--225",
    abstract = "We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination. We demonstrate their effectiveness on generative commonsense reasoning, a.k.a. the CommonGen task, through experiments using both BART and T5 models. Through extensive automatic and human evaluation, we show that SAPPHIRE noticeably improves model performance. An in-depth qualitative analysis illustrates that SAPPHIRE effectively addresses many issues of the baseline model generations, including lack of commonsense, insufficient specificity, and poor fluency.",
}

Autores: Steven Y. Feng, Jessica Huynh, Chaitanya Prasad Narisetty, Eduard Hovy, Varun Gangal

El póster y otros recursos se pueden encontrar aquí .

Nota: Las consultas deben dirigirse a [email protected] o abriendo un problema aquí.

El código se lanzará pronto