Evaluating the Homogeneity of Keyphrase Prediction Models

• URL: http://arxiv.org/abs/2602.12989v1
• Date: Fri, 13 Feb 2026 15:00:35 GMT
• Title: Evaluating the Homogeneity of Keyphrase Prediction Models
• Authors: Maël Houbre, Florian Boudin, Beatrice Daille,
• Abstract summary: Keyphrases which are useful in several NLP and IR applications are either extracted from text or predicted by generative models.<n>Keyphrase generation models can predict keyphrases that do not appear in a document's text.<n>We show that keyphrase extraction methods are competitive with generative models, and that the ability to generate absent keyphrases can actually have a negative impact on homogeneity.
• Score: 5.003135699842281
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Keyphrases which are useful in several NLP and IR applications are either extracted from text or predicted by generative models. Contrarily to keyphrase extraction approaches, keyphrase generation models can predict keyphrases that do not appear in a document's text called `absent keyphrases`. This ability means that keyphrase generation models can associate a document to a notion that is not explicitly mentioned in its text. Intuitively, this suggests that for two documents treating the same subjects, a keyphrase generation model is more likely to be homogeneous in their indexing i.e. predict the same keyphrase for both documents, regardless of those keyphrases appearing in their respective text or not; something a keyphrase extraction model would fail to do. Yet, homogeneity of keyphrase prediction models is not covered by current benchmarks. In this work, we introduce a method to evaluate the homogeneity of keyphrase prediction models and study if absent keyphrase generation capabilities actually help the model to be more homogeneous. To our surprise, we show that keyphrase extraction methods are competitive with generative models, and that the ability to generate absent keyphrases can actually have a negative impact on homogeneity. Our data, code and prompts are available on huggingface and github.

Related papers

• Adapting Dual-encoder Vision-language Models for Paraphrased Retrieval [55.90407811819347]
  We consider the task of paraphrased text-to-image retrieval where a model aims to return similar results given a pair of paraphrased queries. We train a dual-encoder model starting from a language model pretrained on a large text corpus. Compared to public dual-encoder models such as CLIP and OpenCLIP, the model trained with our best adaptation strategy achieves a significantly higher ranking similarity for paraphrased queries.
  arXiv  Detail & Related papers  (2024-05-06T06:30:17Z)
• Retrieval is Accurate Generation [99.24267226311157]
  We introduce a novel method that selects context-aware phrases from a collection of supporting documents. Our model achieves the best performance and the lowest latency among several retrieval-augmented baselines.
  arXiv  Detail & Related papers  (2024-02-27T14:16:19Z)
• 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)
• ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation [59.91139600152296]
  ParaAMR is a large-scale syntactically diverse paraphrase dataset created by abstract meaning representation back-translation. We show that ParaAMR can be used to improve on three NLP tasks: learning sentence embeddings, syntactically controlled paraphrase generation, and data augmentation for few-shot learning.
  arXiv  Detail & Related papers  (2023-05-26T02:27:33Z)
• Neural Keyphrase Generation: Analysis and Evaluation [47.004575377472285]
  We study various tendencies exhibited by three strong models: T5 (based on a pre-trained transformer), CatSeq-Transformer (a non-pretrained Transformer), and ExHiRD (based on a recurrent neural network) We propose a novel metric framework, SoftKeyScore, to evaluate the similarity between two sets of keyphrases.
  arXiv  Detail & Related papers  (2023-04-27T00:10:21Z)
• Applying Transformer-based Text Summarization for Keyphrase Generation [2.28438857884398]
  Keyphrases are crucial for searching and systematizing scholarly documents. In this paper, we experiment with popular transformer-based models for abstractive text summarization. We show that summarization models are quite effective in generating keyphrases in the terms of the full-match F1-score and BERT.Score. We also investigate several ordering strategies to target keyphrases.
  arXiv  Detail & Related papers  (2022-09-08T13:01:52Z)
• Heterogeneous Graph Neural Networks for Keyphrase Generation [13.841525616800908]
  We propose a novel graph-based method that can capture explicit knowledge from related references. Our model first retrieves some document-keyphrases pairs similar to the source document from a pre-defined index as references. To guide the decoding process, a hierarchical attention and copy mechanism is introduced, which directly copies appropriate words from both the source document and its references.
  arXiv  Detail & Related papers  (2021-09-10T07:17:07Z)
• Unsupervised Deep Keyphrase Generation [14.544869226959612]
  Keyphrase generation aims to summarize long documents with a collection of salient phrases. Deep neural models have demonstrated a remarkable success in this task, capable of predicting keyphrases that are even absent from a document. We present a novel method for keyphrase generation, AutoKeyGen, without the supervision of any human annotation.
  arXiv  Detail & Related papers  (2021-04-18T05:53:19Z)
• MASKER: Masked Keyword Regularization for Reliable Text Classification [73.90326322794803]
  We propose a fine-tuning method, coined masked keyword regularization (MASKER), that facilitates context-based prediction. MASKER regularizes the model to reconstruct the keywords from the rest of the words and make low-confidence predictions without enough context. We demonstrate that MASKER improves OOD detection and cross-domain generalization without degrading classification accuracy.
  arXiv  Detail & Related papers  (2020-12-17T04:54:16Z)
• Keyphrase Extraction with Span-based Feature Representations [13.790461555410747]
  Keyphrases are capable of providing semantic metadata characterizing documents. Three approaches to address keyphrase extraction: (i) traditional two-step ranking method, (ii) sequence labeling and (iii) generation using neural networks. In this paper, we propose a novelty Span Keyphrase Extraction model that extracts span-based feature representation of keyphrase directly from all the content tokens.
  arXiv  Detail & Related papers  (2020-02-13T09:48:31Z)

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.