Skip navigation

DSpace JSPUI

DSpace preserves and enables easy and open access to all types of digital content including text, images, moving images, mpegs and data sets

Learn More
DSpace logo
English
中文
  • Browse
    • Communities
      & Collections
    • Publication Year
    • Author
    • Title
    • Subject
    • Advisor
  • Search TDR
  • Rights Q&A
    • My Page
    • Receive email
      updates
    • Edit Profile
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊網路與多媒體研究所
Please use this identifier to cite or link to this item: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85237
Title: 正則化強制指導法於文本摘要的應用
R­TeaFor: Regularized Teacher­-Forcing for Abstractive Summarization
Authors: Guan-Yu Lin
林冠宇
Advisor: 鄭卜壬(Pu-Jen Cheng)
Keyword: 強制指導法,暴露偏差,正則化,文本摘要,自然語言生成,
Teacher-­Forcing,Exposure Bias,Regularization,Text Summarization,Nat­ural Language Generation,
Publication Year : 2022
Degree: 碩士
Abstract: 強制指導法是訓練自然語言生成模型中相當廣泛被使用的方法,該法既可以增加訓練效率,也可以使訓練過程更加穩定。然而,強制指導法會導致相當著名的暴露偏差問題,亦即訓練時模型使用的訓練資料分布與推理時使用的訓練資料分布並不相同。過去的研究通常使用修改訓練資料分布的方式,將訓練資料調整成較相似生成資料分布的形式。上述做法並未考慮原始資料與調整後資料之間的成對關係,因此我們提出正則化強制指導法,在訓練中運用上述的成對關係,提升模型訓練時的正則化效果。實驗數據顯示,正則化強制指導法可以在常見的文本摘要資料集中達到比先前作法更好的效果,且正則化強制指導法可以被應用至不同的預訓練模型中。
Teacher-forcing is widely used in training sequence generation models to improve sampling efficiency and stabilize training. However, teacher-forcing is known for suffering from the exposure bias problem. Previous works have attempted to address exposure bias by modifying the training data to simulate the data distribution in the inference stage. Nevertheless, they do not consider the pairwise relationship between original training data and modified ones. We propose Regularized Teacher-Forcing (R-TeaFor) to utilize this relationship for better regularization. Empirically, we show that R-TeaFor outperforms previous summarization state-of-the-art models, and the results can be generalized to different pre-trained models.
URI: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85237
DOI: 10.6342/NTU202201565
Fulltext Rights: 同意授權(限校園內公開)
metadata.dc.date.embargo-lift: 2022-08-05
Appears in Collections:資訊網路與多媒體研究所

Files in This Item:
File SizeFormat 
U0001-2007202210415900.pdf
Access limited in NTU ip range
3.58 MBAdobe PDF
Show full item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved