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

• URL: http://arxiv.org/abs/2308.08739v2
• Date: Wed, 20 Mar 2024 16:41:11 GMT
• Title: Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extraction
• Authors: Yuanzhen Luo, Qingyu Zhou, Feng Zhou,
• Abstract summary: Keyphrase extraction is an important task in Natural Language Processing. In this study, we propose Diff-KPE to guide the text diffusion process for generating enhanced keyphrase representations. Experiments show that Diff-KPE outperforms existing KPE methods on a large open domain keyphrase extraction benchmark, OpenKP, and a scientific domain dataset, KP20K.
• Score: 9.307602861891926
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• BibRank: Automatic Keyphrase Extraction Platform Using~Metadata [0.0]
  This paper introduces a platform that integrates keyphrase datasets and facilitates the evaluation of keyphrase extraction algorithms. The platform includes BibRank, an automatic keyphrase extraction algorithm that leverages a rich dataset obtained by parsing word in Bib format.
  arXiv  Detail & Related papers  (2023-10-13T14:44:34Z)
• 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)
• Improving Keyphrase Extraction with Data Augmentation and Information Filtering [67.43025048639333]
  Keyphrase extraction is one of the essential tasks for document understanding in NLP. We present a novel corpus and method for keyphrase extraction from the videos streamed on the Behance platform.
  arXiv  Detail & Related papers  (2022-09-11T22:38:02Z)
• LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents [48.84086818702328]
  Identifying keyphrases (KPs) from text documents is a fundamental task in natural language processing and information retrieval. Vast majority of the benchmark datasets for this task are from the scientific domain containing only the document title and abstract information. This presents three challenges for real-world applications: human-written summaries are unavailable for most documents, the documents are almost always long, and a high percentage of KPs are directly found beyond the limited context of title and abstract.
  arXiv  Detail & Related papers  (2022-03-29T08:44:57Z)
• Deep Keyphrase Completion [59.0413813332449]
  Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval. We propose textitkeyphrase completion (KPC) to generate more keyphrases for document (e.g. scientific publication) taking advantage of document content along with a very limited number of known keyphrases. We name it textitdeep keyphrase completion (DKPC) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework
  arXiv  Detail & Related papers  (2021-10-29T07:15:35Z)
• Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding [3.7110020502717616]
  We develop a multimodal Key-phrase extraction approach, namely Phraseformer, using transformer and graph embedding techniques. In Phraseformer, each keyword candidate is presented by a vector which is the concatenation of the text and structure learning representations. We analyze the performance of Phraseformer on three datasets including Inspec, SemEval2010 and SemEval 2017 by F1-score.
  arXiv  Detail & Related papers  (2021-06-09T09:32:17Z)
• 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)
• Capturing Global Informativeness in Open Domain Keyphrase Extraction [40.57116173502994]
  Open-domain KeyPhrase Extraction (KPE) aims to extract keyphrases from documents without domain or quality restrictions. This paper presents JointKPE, an open-domain KPE architecture built on pre-trained language models. JointKPE learns to rank keyphrases by estimating their informativeness in the entire document and is jointly trained on the keyphrase chunking task.
  arXiv  Detail & Related papers  (2020-04-28T16:34:35Z)
• Exclusive Hierarchical Decoding for Deep Keyphrase Generation [63.357895318562214]
  Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases. Previous work in this setting employs a sequential decoding process to generate keyphrases. We propose an exclusive hierarchical decoding framework that includes a hierarchical decoding process and either a soft or a hard exclusion mechanism.
  arXiv  Detail & Related papers  (2020-04-18T02:58:00Z)

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.