@inproceedings{xu-etal-2021-zero,
    title = "Zero-Shot Compositional Concept Learning",
    author = "Xu, Guangyue  and
      Kordjamshidi, Parisa  and
      Chai, Joyce",
    editor = "Lee, Hung-Yi  and
      Mohtarami, Mitra  and
      Li, Shang-Wen  and
      Jin, Di  and
      Korpusik, Mandy  and
      Dong, Shuyan  and
      Vu, Ngoc Thang  and
      Hakkani-Tur, Dilek",
    booktitle = "Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.metanlp-1.3/",
    doi = "10.18653/v1/2021.metanlp-1.3",
    pages = "19--27",
    abstract = "In this paper, we study the problem of recognizing compositional attribute-object concepts within the zero-shot learning (ZSL) framework. We propose an episode-based cross-attention (EpiCA) network which combines merits of cross-attention mechanism and episode-based training strategy to recognize novel compositional concepts. Firstly, EpiCA bases on cross-attention to correlate conceptvisual information and utilizes the gated pooling layer to build contextualized representations for both images and concepts. The updated representations are used for a more indepth multi-modal relevance calculation for concept recognition. Secondly, a two-phase episode training strategy, especially the ransductive phase, is adopted to utilize unlabeled test examples to alleviate the low-resource learning problem. Experiments on two widelyused zero-shot compositional learning (ZSCL) benchmarks have demonstrated the effectiveness of the model compared with recent approaches on both conventional and generalized ZSCL settings."
}