用检索增强方法提升语言模型的命名实体识别效果
Retrieval-Enhanced Named Entity Recognition
- 从训练数据中检索相似样本，增强输入以指导模型识别实体
- 在CrossNER数据集上最高提升11个百分点的F分数
- 不依赖特定模型或检索算法，通用性强适合实际应用
将上下文学习与自回归语言模型结合，可使模型通过输入中的示例直接适应新任务，已在多个任务中取得良好表现。然而，该组合在命名实体识别任务中尚未充分探索，因该任务结构具有独特挑战。本文提出RENER（检索增强命名实体识别），一种基于上下文学习与信息检索技术的命名实体识别方法。当处理输入文本时，RENER从训练样本库中检索出相似示例，用于增强语言模型对目标实体的识别能力。该方法模块化，独立于底层语言模型和检索算法。实验表明，在CrossNER数据集上达到当前最优性能，信息检索可使F-score最高提升11个百分点。
原文摘要 · Abstract (English)
When combined with In-Context Learning, a technique that enables models to adapt to new tasks by incorporating task-specific examples or demonstrations directly within the input prompt, autoregressive language models have achieved good performance in a wide range of tasks and applications. However, this combination has not been properly explored in the context of named entity recognition, where the structure of this task poses unique challenges. We propose RENER (Retrieval-Enhanced Named Entity Recognition), a technique for named entity recognition using autoregressive language models based on In-Context Learning and information retrieval techniques. When presented with an input text, RENER fetches similar examples from a dataset of training examples that are used to enhance a language model to recognize named entities from this input text. RENER is modular and independent of the underlying language model and information retrieval algorithms. Experimental results show that in the CrossNER collection we achieve state-of-the-art performance with the proposed technique and that information retrieval can increase the F-score by up to 11 percentage points.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。