LongKey: Keyphrase Extraction for Long Documents

TL;DR

LongKey is a new framework that effectively extracts keyphrases from long documents using an encoder-based model, outperforming existing methods across multiple datasets and domains.

Contribution

It introduces a novel encoder-based approach with max-pooling for keyphrase extraction from lengthy texts, addressing a gap in current short-document-focused methods.

Findings

LongKey outperforms existing methods on diverse datasets.

It effectively captures long-range dependencies in lengthy texts.

Demonstrates versatility across different domains.

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.