Interpreting Deep Text Quantification Models

被引:0
作者
Bang, YunQi [1 ]
Khaleel, Mohammed [1 ]
Tavanapong, Wallapak [1 ]
机构
[1] Iowa State Univ, Dept Comp Sci, Ames, IA 50011 USA
来源
DATABASE AND EXPERT SYSTEMS APPLICATIONS, DEXA 2023, PT II | 2023年 / 14147卷
关键词
Deep learning; Interpretation; Quantification;
D O I
10.1007/978-3-031-39821-6_25
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Quantification learning is a relatively new deep learning task. Differing from a classic classification problem where the class of a single instance is predicted, a quantification model predicts the distribution of classes within a given set of instances. Quantification learning has applications in various domains. For example, in designing political campaign ads, it is important to know the proportion of different aspects voters care about. QuaNet is a recent deep learning quantification model that was shown to achieve good quantification performance. Like many deep learning models, there is no explanation about the contributions of different inputs QuaNet uses to predict a class distribution. In this study, we propose a method to provide such an explanation, which is important to increase users' trust in the model. Our method is the first work on interpreting deep learning quantification models.
引用
收藏
页码:310 / 324
页数:15
相关论文
共 50 条
  • [41] A Systematic Literature Review on Text Generation Using Deep Neural Network Models
    Fatima, Noureen
    Imran, Ali Shariq
    Kastrati, Zenun
    Daudpota, Sher Muhammad
    Soomro, Abdullah
    IEEE ACCESS, 2022, 10 : 53490 - 53503
  • [42] Uncertainty Quantification of Contaminated Soil Volume with Deep Neural Networks and Predictive Models
    Guridi, Ignacio
    Chassagne, Romain
    Pryet, Alexandre
    Atteia, Olivier
    ENVIRONMENTAL MODELING & ASSESSMENT, 2024, 29 (03) : 621 - 640
  • [43] Ensemble deep learning models for prediction and uncertainty quantification of ground magnetic perturbation
    Siddique, Talha
    Mahmud, Md Shaad
    FRONTIERS IN ASTRONOMY AND SPACE SCIENCES, 2022, 9
  • [44] Automatic plankton quantification using deep features
    Gonzalez, Pablo
    Castano, Alberto
    Peacock, Emily E.
    Diez, Jorge
    Jose Del Coz, Juan
    Sosik, Heidi M.
    JOURNAL OF PLANKTON RESEARCH, 2019, 41 (04) : 449 - 463
  • [45] An experimental quantification of messages returned in the learning curve for interpreting
    Shao Wei
    Yang Peiyan
    FORUM-REVUE INTERNATIONALE D INTERPRETATION ET DE TRADUCTION-INTERNATIONAL JOURNAL OF INTERPRETATION AND TRANSLATION, 2013, 11 (01): : 223 - 255
  • [46] Deep Neural Models for Chronic Disease Status Detection in Free Text Clinical Records
    Rajput, Kunal
    Chetty, Girija
    Davey, Rachel
    2018 18TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2018, : 864 - 869
  • [47] Extracting Decision Model and Notation models from text using deep learning techniques
    Goossens, Alexandre
    De Smedt, Johannes
    Vanthienen, Jan
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 211
  • [48] Factors in Emotion Recognition With Deep Learning Models Using Speech and Text on Multiple Corpora
    Braunschweiler, Norbert
    Doddipatla, Rama
    Keizer, Simon
    Stoyanchev, Svetlana
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 722 - 726
  • [49] Planning the development of text-to-speech synthesis models and datasets with dynamic deep learning
    Ahmad, Hawraz A.
    Rashid, Tarik A.
    JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2024, 36 (07)
  • [50] DAMAGE QUANTIFICATION OF HIGH-RATE IMPACTS USING HYBRID DEEP LEARNING MODELS
    Todisco, Mark
    Mao, Zhu
    PROCEEDINGS OF ASME 2021 INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION (IMECE2021), VOL 4, 2021,