Please use this identifier to cite or link to this item:
Title: Syntactic manipulation for generating more diverse and interesting texts
Authors : Deriu, Jan Milan
Cieliebak, Mark
Proceedings: Proceedings of the 11th International Conference on Natural Language Generation
Pages : 22
Pages to: 34
Conference details: 11th International Conference on Natural Language Generation (INLG 2018), Tilburg, The Netherlands, 05-08 November 2018
Publisher / Ed. Institution : Association for Computational Linguistics
Issue Date: 2018
License (according to publishing contract) : CC BY 4.0: Attribution 4.0 International
Type of review: Peer review (Publication)
Language : English
Subjects : Natural language generation; Natural language processing; Deep neural networks; Neural networks; Text embellishment
Subject (DDC) : 005: Computer programming, programs and data
410.285: Computational linguistics
Abstract: Natural Language Generation plays an important role in the domain of dialogue systems as it determines how users perceive the system. Recently, deep-learning based systems have been proposed to tackle this task, as they generalize better and require less amounts of manual effort to implement them for new domains. However, deep learning systems usually adapt a very homogeneous sounding writing style which expresses little variation. In this work, we present our system for Natural Language Generation where we control various aspects of the surface realization in order to increase the lexical variability of the utterances, such that they sound more diverse and interesting. For this, we use a Semantically Controlled Long Short-term Memory Network (SCLSTM), and apply its specialized cell to control various syntactic features of the generated texts. We present an in-depth human evaluation where we show the effects of these surface manipulation on the perception of potential users.
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Publication type: Conference Paper
DOI : 10.21256/zhaw-4875
Appears in Collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2018_Deriu_Syntactic_manipulation_for_generating_more_diverse_and_interesting_texts.pdf276.23 kBAdobe PDFThumbnail

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