A Joint Learning Approach based on Self-Distillation for Keyphrase Extraction from Scientific Documents
This work addresses the problem of data scarcity in keyphrase extraction for scientific documents, offering an incremental improvement over existing methods.
The paper tackles the challenge of limited annotated data for keyphrase extraction by proposing a joint learning approach using self-distillation to leverage unlabeled scientific articles, achieving new state-of-the-art results on Inspec and SemEval-2017 benchmarks.
Keyphrase extraction is the task of extracting a small set of phrases that best describe a document. Most existing benchmark datasets for the task typically have limited numbers of annotated documents, making it challenging to train increasingly complex neural networks. In contrast, digital libraries store millions of scientific articles online, covering a wide range of topics. While a significant portion of these articles contain keyphrases provided by their authors, most other articles lack such kind of annotations. Therefore, to effectively utilize these large amounts of unlabeled articles, we propose a simple and efficient joint learning approach based on the idea of self-distillation. Experimental results show that our approach consistently improves the performance of baseline models for keyphrase extraction. Furthermore, our best models outperform previous methods for the task, achieving new state-of-the-art results on two public benchmarks: Inspec and SemEval-2017.