面向少样本命名实体识别的大规模标签解释学习
Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition
AI总结：
本文提出通过大规模增加标签解释学习的实体类型数量和粒度，利用强语义先验提升少样本命名实体识别性能，在零样本及少样本的领域内、跨领域和跨语言设置中均取得显著效果。
摘要：
少样本命名实体识别（NER）仅使用少量标注示例来检测文本中的命名实体。一个有前景的研究方向是利用每种实体类型的自然语言描述：例如，通用标签 PER可能被表述为“person entity”。在初始的标签解释学习阶段，模型学习解释此类实体类型的表述描述。在随后的少样本标签集扩展阶段，该模型随后被给予一个未见过的实体类型（如“music album”）的描述，并可选择性地提供少量训练示例，以对该类型执行少样本 NER。在本文中，我们通过大规模增加用于标签解释学习的实体类型的数量和粒度，系统地探索了强语义先验对解释新实体类型表述的影响。为此，我们利用一个实体链接基准创建了一个数据集，其包含的不同实体类型和描述的数量比目前使用的数据集多出几个数量级。我们发现，这种增加的信号在领域内、跨领域甚至跨语言设置的零样本和少样本 NER 中产生了强劲的结果。我们的发现表明，通过基于启发式的数据优化来改进少样本 NER 具有巨大潜力。
英文摘要：
Few-shot named entity recognition (NER) detects named entities within text using only a few annotated examples. One promising line of research is to leverage natural language descriptions of each entity type: the common label PER might, for example, be verbalized as ''person entity.'' In an initial label interpretation learning phase, the model learns to interpret such verbalized descriptions of entity types. In a subsequent few-shot tagset extension phase, this model is then given a description of a previously unseen entity type (such as ''music album'') and optionally a few training examples to perform few-shot NER for this type. In this paper, we systematically explore the impact of a strong semantic prior to interpret verbalizations of new entity types by massively scaling up the number and granularity of entity types used for label interpretation learning. To this end, we leverage an entity linking benchmark to create a dataset with orders of magnitude of more distinct entity types and descriptions as currently used datasets. We find that this increased signal yields strong results in zero- and few-shot NER in in-domain, cross-domain, and even cross-lingual settings. Our findings indicate significant potential for improving few-shot NER through heuristical data-based optimization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
