Title page for etd-0708118-120036


[Back to Results | New Search]

URN etd-0708118-120036
Author Yung-Chieh Chou
Author's Email Address No Public.
Statistics This thesis had been viewed 5340 times. Download 231 times.
Department Information Management
Year 2017
Semester 2
Degree Master
Type of Document
Language English
Title Automatic Term Explanation based on Topic-regularized Recurrent Neural Network
Date of Defense 2018-07-20
Page Count 38
Keyword
  • Recurrent neural network
  • Automatic sentence generation
  • Automatic term explanation
  • Automatic summarization
  • Nonnegative matrix factorization
  • Topic model
  • Long short-term memory
  • Abstract In this study, we propose a topic-regularized Recurrent Neural Network(RNN)-based model designed to explain given terms. RNN-based models usually generate text results that have correct syntax but lack coherence, whereas topic models produce several topics consisting of coherent keywords. Here we consider combining them into a new model that takes advantages of both. In our experiment, we trained Long Short-Term Memory (LSTM) models on selected articles that mention given terms, applying nonsmooth nonnegative matrix factorization(nsNMF) on document-term matrix to obtain contextual biases. Our empirical results showed that topic-regularizing LSTM outperforms original models while generating readable sentences. Additionally, topic-regularized LSTM could adopt different topics to generate description about subtle but important aspects of a certain field, which is usually not captured by original LSTM.
    Advisory Committee
  • Keng-Pei Lin - chair
  • Pei-Ju Lee - co-chair
  • Yi-huang Kang - advisor
  • Files
  • etd-0708118-120036.pdf
  • indicate access worldwide
    Date of Submission 2018-08-10

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys