Keyphrase generation (KG) aims to generate a set of summarizing words or
phrases given a source document, while keyphrase extraction (KE) aims to
identify them from the text. Because the search space is much smaller in KE, it
is often combined with KG to predict keyphrases that may or may not exist in
the corresponding document. However, current unified approaches adopt sequence
labeling and maximization-based generation that primarily operate at a token
level, falling short in observing and scoring keyphrases as a whole. In this
work, we propose SimCKP, a simple contrastive learning framework that consists
of two stages: 1) An extractor-generator that extracts keyphrases by learning
context-aware phrase-level representations in a contrastive manner while also
generating keyphrases that do not appear in the document; 2) A reranker that
adapts scores for each generated phrase by likewise aligning their
representations with the corresponding document. Experimental results on
multiple benchmark datasets demonstrate the effectiveness of our proposed
approach, which outperforms the state-of-the-art models by a significant
margin.

我们提出了一个简单的对比学习框架 SimCKP，它由两个阶段组成：1）一个提取器 - 生成器，通过对比学习的方式学习上下文感知的短语级表示，同时生成不出现在文档中的关键短语；2）一个重新排序器，通过将生成的短语的表示与相应的文档对齐来调整每个短语的得分。在多个基准数据集上的实验结果证明了我们提出的方法的有效性，其性能明显优于现有的模型。