English

Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extraction

Computation and Language 2024-03-21 v2

Abstract

Keyphrase extraction (KPE) is an important task in Natural Language Processing for many scenarios, which aims to extract keyphrases that are present in a given document. Many existing supervised methods treat KPE as sequential labeling, span-level classification, or generative tasks. However, these methods lack the ability to utilize keyphrase information, which may result in biased results. In this study, we propose Diff-KPE, which leverages the supervised Variational Information Bottleneck (VIB) to guide the text diffusion process for generating enhanced keyphrase representations. Diff-KPE first generates the desired keyphrase embeddings conditioned on the entire document and then injects the generated keyphrase embeddings into each phrase representation. A ranking network and VIB are then optimized together with rank loss and classification loss, respectively. This design of Diff-KPE allows us to rank each candidate phrase by utilizing both the information of keyphrases and the document. Experiments show that Diff-KPE outperforms existing KPE methods on a large open domain keyphrase extraction benchmark, OpenKP, and a scientific domain dataset, KP20K.

Keywords

Cite

@article{arxiv.2308.08739,
  title  = {Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extraction},
  author = {Yuanzhen Luo and Qingyu Zhou and Feng Zhou},
  journal= {arXiv preprint arXiv:2308.08739},
  year   = {2024}
}

Comments

10 pages, 2 figures, accepted to LREC-COLING 2024

R2 v1 2026-06-28T11:57:36.137Z