One2set + 大语言模型：关键短语生成的最佳搭档
One2set + Large Language Model: Best Partners for Keyphrase Generation
AI总结：
针对关键短语生成中召回与精确难以兼顾的问题，提出先生成后选择框架，以 one2set 模型生成候选并用大语言模型选择，通过最优传输分配和序列标注选择实现性能显著提升。
摘要：
关键短语生成（KPG）旨在自动生成一组能够代表给定文档核心概念的短语。KPG 中的主流范式包括 one2seq 和 one2set。近年来，将大语言模型（LLMs）应用于 KPG 的兴趣日益增长。我们的初步实验表明，单一模型很难同时在召回率和精确率上都表现出色。进一步分析显示：1）one2set 范式具有高召回率的优势，但在训练过程中存在监督信号分配不当的问题；2）LLMs 在关键短语选择方面能力强大，但现有的选择方法常常产生冗余选择。基于这些观察，我们提出了一个先生成后选择的框架，将 KPG 分解为两个步骤：采用基于 one2set 的模型作为生成器来产生候选短语，然后使用 LLM 作为选择器从这些候选中挑选关键短语。特别地，我们对生成器和选择器做了两项重要改进：1）设计了一种基于最优传输的分配策略来解决上述分配不当问题；2）将关键短语选择建模为序列标注任务以缓解冗余选择。在多个基准数据集上的实验结果表明，我们的框架显著超越了最先进的模型，尤其是在缺失关键短语预测方面。
英文摘要：
Keyphrase generation (KPG) aims to automatically generate a collection of phrases representing the core concepts of a given document. The dominant paradigms in KPG include one2seq and one2set. Recently, there has been increasing interest in applying large language models (LLMs) to KPG. Our preliminary experiments reveal that it is challenging for a single model to excel in both recall and precision. Further analysis shows that: 1) the one2set paradigm owns the advantage of high recall, but suffers from improper assignments of supervision signals during training; 2) LLMs are powerful in keyphrase selection, but existing selection methods often make redundant selections. Given these observations, we introduce a generate-then-select framework decomposing KPG into two steps, where we adopt a one2set-based model as generator to produce candidates and then use an LLM as selector to select keyphrases from these candidates. Particularly, we make two important improvements on our generator and selector: 1) we design an Optimal Transport-based assignment strategy to address the above improper assignments; 2) we model the keyphrase selection as a sequence labeling task to alleviate redundant selections. Experimental results on multiple benchmark datasets show that our framework significantly surpasses state-of-the-art models, especially in absent keyphrase prediction.
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。
