LongKey: Keyphrase Extraction for Long Documents

Abstract

In an era of information overload, manually annotating the vast and growing corpus of documents and scholarly papers is increasingly impractical. Automated keyphrase extraction addresses this challenge by identifying representative terms within texts. However, most existing methods focus on short documents (up to 512 tokens), leaving a gap in processing long-context documents. In this paper, we introduce LongKey, a novel framework for extracting keyphrases from lengthy documents, which uses an encoder-based language model to capture extended text intricacies. LongKey uses a max-pooling embedder to enhance keyphrase candidate representation. Validated on the comprehensive LDKP datasets and six diverse, unseen datasets, LongKey consistently outperforms existing unsupervised and language model-based keyphrase extraction methods. Our findings demonstrate LongKey's versatility and superior performance, marking an advancement in keyphrase extraction for varied text lengths and domains.

Accepted for presentation at the 2024 IEEE International Conference on Big Data (IEEE BigData 2024). Code available at https://github.com/jeohalves/longkey

References in corpus (6)

• Longformer: The Long-Document Transformer
• PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction
• LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents
• Two Huge Title and Keyword Generation Corpora of Research Articles
• Enhancing Keyphrase Extraction from Long Scientific Documents using Graph Embeddings
• Detecting Relevant Information in High-Volume Chat Logs: Keyphrase Extraction for Grooming and Drug Dealing Forensic Analysis