MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction

• URL: http://arxiv.org/abs/2605.00597v1
• Date: Fri, 01 May 2026 12:10:14 GMT
• Title: MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction
• Abstract summary: Keyphrase extraction aims to automatically identify concise phrases that effectively represent a document.<n>Recent methods leveraging pre-trained language models (PLMs) have significantly improved the extraction of keyphrases with strong global semantic relevance.<n>We propose a novel context-centric framework, MUDY, that effectively captures multi-granular contextual salience of candidate keyphrases.
• Score: 10.20513220388712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Keyphrase extraction aims to automatically identify concise phrases that effectively represent the content of a document. While recent methods leveraging pre-trained language models (PLMs) have significantly improved the extraction of keyphrases with strong global semantic relevance, they often fall short in capturing the local contextual importance of keyphrases tied to specific subtopics dispersed in a document. In this paper, we propose a novel context-centric framework, MUDY, that effectively captures multi-granular contextual salience of candidate keyphrases. MUDY employs two complementary components: (1) a prompt-based scoring that estimates the generation likelihood of each candidate keyphrase, augmented with candidate-aware weighting to better reflect its local contextual importance, and (2) a self-attention-based scoring that utilizes multi-granular attention patterns from PLMs to assess candidate significance at both the document-wide and segment-specific levels. Evaluations on four real-world datasets demonstrate that MUDY outperforms state-of-the-art baselines in top-k accuracy at various cutoff thresholds. In-depth quantitative and qualitative analyses further highlight the efficacy of context-centric keyphrase extraction with multi-granular saliency. For reproducibility, the source code of MUDY is available at https://github.com/HgKang1/MUDY.

Related papers

• SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space [11.534994345027362]
  Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation.<n>We introduce a novel adversarial paraphrasing task: generating grammatically correct paraphrases that preserve the original query meaning while degrading segmentation performance.<n>We introduce SPARTA-a black-box, sentence-level optimization method that operates in the low-dimensional semantic latent space of a text autoencoder.
  arXiv  Detail & Related papers  (2025-10-28T14:09:05Z)
• Learning Multi-Aspect Item Palette: A Semantic Tokenization Framework for Generative Recommendation [55.99632509895994]
  We introduce LAMIA, a novel approach for multi-aspect semantic tokenization.<n>Unlike RQ-VAE, which uses a single embedding, LAMIA learns an item palette''--a collection of independent and semantically parallel embeddings.<n>Our results demonstrate significant improvements in recommendation accuracy over existing methods.
  arXiv  Detail & Related papers  (2024-09-11T13:49:48Z)
• MetaKP: On-Demand Keyphrase Generation [52.48698290354449]
  We introduce on-demand keyphrase generation, a novel paradigm that requires keyphrases that conform to specific high-level goals or intents. We present MetaKP, a large-scale benchmark comprising four datasets, 7500 documents, and 3760 goals across news and biomedical domains with human-annotated keyphrases. We demonstrate the potential of our method to serve as a general NLP infrastructure, exemplified by its application in epidemic event detection from social media.
  arXiv  Detail & Related papers  (2024-06-28T19:02:59Z)
• SimCKP: Simple Contrastive Learning of Keyphrase Representations [36.88517357720033]
  We propose SimCKP, a simple contrastive learning framework that consists of two stages: 1) An extractor-generator that extracts keyphrases by learning context-aware phrase-level representations in a contrastive manner while also generating keyphrases that do not appear in the document; and 2) A reranker that adapts scores for each generated phrase by likewise aligning their representations with the corresponding document.
  arXiv  Detail & Related papers  (2023-10-12T11:11:54Z)
• Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering [79.44443231700201]
  Multi-modal keyphrase generation aims to produce a set of keyphrases that represent the core points of the input text-image pair. The input text and image are often not perfectly matched, and thus the image may introduce noise into the model. We propose a novel multi-modal keyphrase generation model, which not only enriches the model input with external knowledge, but also effectively filters image noise.
  arXiv  Detail & Related papers  (2023-09-09T09:41:36Z)
• Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training [66.64843711515341]
  Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. We call attention to a new setting named multilingual keyphrase generation. We propose a retrieval-augmented method for multilingual keyphrase generation to mitigate the data shortage problem in non-English languages.
  arXiv  Detail & Related papers  (2022-05-21T00:45:21Z)
• Representation Learning for Resource-Constrained Keyphrase Generation [78.02577815973764]
  We introduce salient span recovery and salient span prediction as guided denoising language modeling objectives. We show the effectiveness of the proposed approach for low-resource and zero-shot keyphrase generation.
  arXiv  Detail & Related papers  (2022-03-15T17:48:04Z)
• Unsupervised Keyphrase Extraction via Interpretable Neural Networks [27.774524511005172]
  Keyphrases that are most useful for predicting the topic of a text are important keyphrases. InSPECT is a self-explaining neural framework for identifying influential keyphrases. We show that INSPECT achieves state-of-the-art results in unsupervised key extraction across four diverse datasets.
  arXiv  Detail & Related papers  (2022-03-15T04:30:47Z)
• Enhancing Keyphrase Extraction from Academic Articles with their Reference Information [12.769066804715697]
  Keyphrases that summarize document information highly are helpful for users to quickly obtain and understand documents. Title information in references also contains author-assigned keyphrases. Experiments show reference information can increase precision, recall, and F1 of automatic keyphrase extraction.
  arXiv  Detail & Related papers  (2021-11-28T11:14:16Z)
• Importance Estimation from Multiple Perspectives for Keyphrase Extraction [34.51718374923614]
  We propose a new approach to estimate the importance of keyphrase from multiple perspectives (called as textitKIEMP) textitKIEMP estimates the importance of phrase with three modules: a chunking module to measure its syntactic accuracy, a ranking module to check its information saliency, and a matching module to judge the concept consistency between phrase and the whole document. Experimental results on six benchmark datasets show that textitKIEMP outperforms the existing state-of-the-art keyphrase extraction approaches in most cases.
  arXiv  Detail & Related papers  (2021-10-19T05:48:22Z)
• Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference [50.768682650658384]
  Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document. Recent Sequence-to-Sequence (Seq2Seq) based generative framework is widely used in KE task, and it has obtained competitive performance on various benchmarks. In this paper, we propose to adopt the Dynamic Graph Convolutional Networks (DGCN) to solve the above two problems simultaneously.
  arXiv  Detail & Related papers  (2020-10-24T08:11:23Z)
• GLEAKE: Global and Local Embedding Automatic Keyphrase Extraction [1.0681288493631977]
  We introduce Global and Local Embedding Automatic Keyphrase Extractor (GLEAKE) for the task of automatic keyphrase extraction. GLEAKE uses single and multi-word embedding techniques to explore the syntactic and semantic aspects of the candidate phrases. It refines the most significant phrases as a final set of keyphrases.
  arXiv  Detail & Related papers  (2020-05-19T20:24:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.