@inproceedings{ren-etal-2020-two,
    title = "A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification",
    author = "Ren, Haopeng  and
      Cai, Yi  and
      Chen, Xiaofeng  and
      Wang, Guohua  and
      Li, Qing",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.coling-main.142/",
    doi = "10.18653/v1/2020.coling-main.142",
    pages = "1618--1629",
    abstract = "Relation Classification (RC) plays an important role in natural language processing (NLP). Current conventional supervised and distantly supervised RC models always make a closed-world assumption which ignores the emergence of novel relations in open environment. To incrementally recognize the novel relations, current two solutions (i.e, re-training and lifelong learning) are designed but suffer from the lack of large-scale labeled data for novel relations. Meanwhile, prototypical network enjoys better performance on both fields of deep supervised learning and few-shot learning. However, it still suffers from the incompatible feature embedding problem when the novel relations come in. Motivated by them, we propose a two-phase prototypical network with prototype attention alignment and triplet loss to dynamically recognize the novel relations with a few support instances meanwhile without catastrophic forgetting. Extensive experiments are conducted to evaluate the effectiveness of our proposed model."
}