@inproceedings{xu-etal-2023-dense,
    title = "Dense Retrieval as Indirect Supervision for Large-space Decision Making",
    author = "Xu, Nan  and
      Wang, Fei  and
      Dong, Mingtao  and
      Chen, Muhao",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-emnlp.1002/",
    doi = "10.18653/v1/2023.findings-emnlp.1002",
    pages = "15021--15033",
    abstract = "Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of selection among many fine-grained labels. Inspired by dense retrieval methods for passage finding in open-domain QA, we propose a reformulation of large-space discriminative NLU tasks as a learning-to-retrieve task, leading to a novel solution named Dense Decision Retrieval (DDR). Instead of predicting fine-grained decisions as logits, DDR adopts a dual-encoder architecture that learns to predict by retrieving from a decision thesaurus. This approach not only leverages rich indirect supervision signals from easy-to-consume learning resources for dense retrieval, it also leads to enhanced prediction generalizability with a semantically meaningful representation of the large decision space. When evaluated on tasks with decision spaces ranging from hundreds to hundred-thousand scales, DDR outperforms strong baselines greatly by 27.54{\%} in P @1 on two extreme multi-label classification tasks, 1.17{\%} in F1 score ultra-fine entity typing, and 1.26{\%} in accuracy on three few-shot intent classification tasks on average."
}