| DC 欄位 |
值 |
語言 |
| DC.contributor | 資訊工程學系 | zh_TW |
| DC.creator | 楊若函 | zh_TW |
| DC.creator | Jo-Han Yang | en_US |
| dc.date.accessioned | 2021-10-19T07:39:07Z | |
| dc.date.available | 2021-10-19T07:39:07Z | |
| dc.date.issued | 2021 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=108552022 | |
| dc.contributor.department | 資訊工程學系 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.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。 | zh_TW |
| dc.description.abstract | With the development of classification methods based on deep learning,
hierarchical classification tasks with new class detection began to attract researchers’ 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 topdown 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. | en_US |
| DC.subject | 自然語言處理 | zh_TW |
| DC.subject | 階層式文字分類 | zh_TW |
| DC.subject | 階層式新類偵測 | zh_TW |
| DC.subject | Nature Language Processing | en_US |
| DC.subject | Hierarchical Text Classification | en_US |
| DC.subject | Hierarchical Novelty Detection | en_US |
| DC.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 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Hierarchical text classification with novelty detection for evolving taxonomies | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |