Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Learning to predict text quality using Generative Adversarial Networks
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Numerical Analysis, NA.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Prediktion av textkvalitet med generativa kontradiktoriska nätverk (Swedish)
Abstract [en]

Generating summaries of long text articles is a common application in natural language processing. Automatic text summarization models often find themselves generating summaries that don’t resemble the quality of human written text, even though they preserve factual accuracy. In this thesis, a method to improve quality of summaries is created by combining loss functions from an existing baseline competitive model (Pointer Generator Networks) for abstractive text summarization with SeqGAN - a successful text generation algorithm based on Generative Adversarial Networks. The model is tested on the CNN/Daily Mail dataset of news articles. The results show that the summaries generated by the model are more human-like in quality as well as accurate in content than the baseline model.

Abstract [sv]

Att generera sammanfattningar av långa artiklar är en vanlig tillämpning inom språkteknologi. Automatiska textsammanfattningsmodeller ger ofta sammanfattningar som inte håller samma kvalitet som människoskriven text, även om den faktiska noggrannheten i textens innehåll är bevarad. I denna avhandling presenteras en metod för att förbättra kvaliteten hos automatiskt genererade textsammanfattningar, vilken kombinerar förlustfunktioner från en existerande modell (Pointer Generator Networks) för automatisk generering av textsammanfattningar med SeqGAN - en framgångsrik textgenereringsalgoritm baserad på generativa kontradiktoriska nätverk (eng. Generative Adversarial Networks). Modellen testas på en uppsättning nyhetsartiklar från CNN/Daily Mail. Resultaten visar att sammanfattningarna som genereras av modellen är såväl kvalitetsmässigt som innehållsmässigt mer lika den människoskrivna texten jämfört med modellen baserad på Pointer Generator Networks.

Place, publisher, year, edition, pages
2019.
Series
TRITA-SCI-GRU ; 2019:397
National Category
Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-264109OAI: oai:DiVA.org:kth-264109DiVA, id: diva2:1372108
External cooperation
Peltarion
Subject / course
Scientific Computing
Educational program
Master of Science - Computer Simulation for Science and Engineering
Supervisors
Examiners
Available from: 2019-11-22 Created: 2019-11-22 Last updated: 2019-11-22Bibliographically approved

Open Access in DiVA

fulltext(2699 kB)16 downloads
File information
File name FULLTEXT02.pdfFile size 2699 kBChecksum SHA-512
dc59c9f89691057b2bc4b351b10bd9f63f33ce0206119d34ad13206a34575054b04a1ac89e0d21546b76ca09e53d7d5d171581dddf04a580f9ef7efcfd71c240
Type fulltextMimetype application/pdf

By organisation
Numerical Analysis, NA
Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 18 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 30 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf