• search hit 7 of 23
Back to Result List

Hypothesis extraction from scientific papers with sequential generative adversarial neural network for theory ontology learning.

  • In this study, we investigate the usage of generative adversarial neural networks(GAN) for a sequence labeling task. We applied sequence generative adversarial neural network (SeqGAN) to extract cause-effect and moderator-mediator relations from hypotheses from scientific papers. This research focuses on the structure of SeqGAN and the problems that come with it. However, there are two main problems with GAN’s. Firstly, a vanilla GAN (Goodfellow et. Al. 2014) is designed for generating real-valued, continuous data but we want to label discrete words into tokens. The second problem is that a GAN can only provide a loss for a complete sequence (Yu, Zhang, Wang, & Yu, 2017, p. 1). To address these problems two things are changed. First, the sequence generation process is realized as a decisionmaking process. The sequences are going to be evaluated by the discriminator model. To solve the problem with the discrete data we follow Yu et. Al. and regard the generative model as a policy gradient. To approximate the sequence value a Monte Carlo Search is employed in the generative model. We show the performance of different parameter settings and which tricks improve the results. The python and r scripts are appended in this document. They can also be found in GitHub (https://github.com/clamkewitz/GANCause).

Download full text files

  • Lamkewitz,Christian_MA_2019.pdf
    eng

    verfügbar innerhalb des Netzes der HWR Berlin

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Christian Lamkewitz
Referee:Roland Müller
Advisor:Markus Löcher
Document Type:Master's Thesis
Language:English
Date of first Publication:2019/08/13
Publishing Institution:Hochschulbibliothek HWR Berlin
Granting Institution:Hochschule für Wirtschaft und Recht Berlin
Date of final exam:2019/01/28
Release Date:2019/08/13
Tag:Gradient Policy; Monte Carlo Search; Ontology Learning; Sequence Generative Adversarial Nets; Sequence Labeling
Page Number:91
Institutes:FB I - Wirtschaftswissenschaften / Business Intelligence and Process Management M.Sc.
Licence (German):License LogoUrheberrechtsschutz