用於不斷發展的分類法之具備新穎性檢 測的分層文本分類技術;Hierarchical text classification with novelty detection for evolving taxonomies

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/86834

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/86834

Title:	用於不斷發展的分類法之具備新穎性檢測的分層文本分類技術;Hierarchical text classification with novelty detection for evolving taxonomies
Authors:	楊若函;Yang, Jo-Han
Contributors:	資訊工程學系
Keywords:	自然語言處理;階層式文字分類;階層式新類偵測;Nature Language Processing;Hierarchical Text Classification;Hierarchical Novelty Detection
Date:	2021-10-19
Issue Date:	2021-12-07 13:18:32 (UTC+8)
Publisher:	國立中央大學
Abstract:	在深度學習的領域中，分類任務的技術越趨成熟，而近年來相關研究人員也陸續投身於具備新穎性檢測的階層式分類方法。我們在此篇論文提出了一個利用分解信心值和連接條件機率，達到具新穎性檢測的階層式分類模型，且訓練過程中不需加入額外的新類別資料，而基準模型包含了自頂向下方法及攤平方法。將我們提出的模型與基準模型相互比較，從結果可以得知，我們的模型除了有效提升已知類別的準確度外，於尋找新的分類上也更加精準。此外針對階層式新類偵測的任務，論文中提出了一個新的算分方法，目的是同時考慮新類偵測以及階層式分類兩個任務，使其能更精確地顯示出模型的效能。;With the development of classification methods based on deep learning, hierarchical classification tasks with new class detection began to attract re searchers’ attention. In this paper, we propose a hierarchical classification with a novelty detection model by decomposing confidence and concatenating conditional probability, which can be trained without labeled novelty data. We compare it with a baseline model that combines the top?down method and flatten method. From the results, we found that our model can improve the classification accuracy of known categories and find instances belonging to new categories more effectively. We propose a new evaluation metric for the hierarchical novelty detection task. It considers both novelty detection and hierarchical classification so that it is able to express the performance of the model more obviously.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	106	View/Open

社群 sharing

Loading...