ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Do, Lam Thanh, Bodke, Aaditya, Akash, Pritom Saha, Chang, Kevin Chen-Chuan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916767394168832
author Do, Lam Thanh
Bodke, Aaditya
Akash, Pritom Saha
Chang, Kevin Chen-Chuan
author_facet Do, Lam Thanh
Bodke, Aaditya
Akash, Pritom Saha
Chang, Kevin Chen-Chuan
contents Unsupervised keyphrase prediction has gained growing interest in recent years. However, existing methods typically rely on heuristically defined importance scores, which may lead to inaccurate informativeness estimation. In addition, they lack consideration for time efficiency. To solve these problems, we propose ERU-KG, an unsupervised keyphrase generation (UKG) model that consists of an informativeness and a phraseness module. The former estimates the relevance of keyphrase candidates, while the latter generate those candidates. The informativeness module innovates by learning to model informativeness through references (e.g., queries, citation contexts, and titles) and at the term-level, thereby 1) capturing how the key concepts of documents are perceived in different contexts and 2) estimating informativeness of phrases more efficiently by aggregating term informativeness, removing the need for explicit modeling of the candidates. ERU-KG demonstrates its effectiveness on keyphrase generation benchmarks by outperforming unsupervised baselines and achieving on average 89\% of the performance of a supervised model for top 10 predictions. Additionally, to highlight its practical utility, we evaluate the model on text retrieval tasks and show that keyphrases generated by ERU-KG are effective when employed as query and document expansions. Furthermore, inference speed tests reveal that ERU-KG is the fastest among baselines of similar model sizes. Finally, our proposed model can switch between keyphrase generation and extraction by adjusting hyperparameters, catering to diverse application requirements.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24219
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation
Do, Lam Thanh
Bodke, Aaditya
Akash, Pritom Saha
Chang, Kevin Chen-Chuan
Computation and Language
Unsupervised keyphrase prediction has gained growing interest in recent years. However, existing methods typically rely on heuristically defined importance scores, which may lead to inaccurate informativeness estimation. In addition, they lack consideration for time efficiency. To solve these problems, we propose ERU-KG, an unsupervised keyphrase generation (UKG) model that consists of an informativeness and a phraseness module. The former estimates the relevance of keyphrase candidates, while the latter generate those candidates. The informativeness module innovates by learning to model informativeness through references (e.g., queries, citation contexts, and titles) and at the term-level, thereby 1) capturing how the key concepts of documents are perceived in different contexts and 2) estimating informativeness of phrases more efficiently by aggregating term informativeness, removing the need for explicit modeling of the candidates. ERU-KG demonstrates its effectiveness on keyphrase generation benchmarks by outperforming unsupervised baselines and achieving on average 89\% of the performance of a supervised model for top 10 predictions. Additionally, to highlight its practical utility, we evaluate the model on text retrieval tasks and show that keyphrases generated by ERU-KG are effective when employed as query and document expansions. Furthermore, inference speed tests reveal that ERU-KG is the fastest among baselines of similar model sizes. Finally, our proposed model can switch between keyphrase generation and extraction by adjusting hyperparameters, catering to diverse application requirements.
title ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation
topic Computation and Language
url https://arxiv.org/abs/2505.24219