Change search
ReferencesLink to record
Permanent link

Direct link
Natural Language Interface technology in computer games: AN EVALUATION OF NATURAL LANGUAGE PARSERS IN COMPUTER GAMES
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2015 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

A Natural Language Interface is an interface that operates on language input rather thanmouse and keyboard. It works by parsing the input into terms, and then parsing these termsinto a logic statement that can be processed. The efficiency and viability of Natural LanguageInterfaces in computer games was compared to the normal input of keyboard and mouse.This was done by having test users play a game with NLI and then running their inputsthrough a semantic parser. The results indicate that NLI in its current state is less efficient asa way of input than the keyboard/mouse way.

Abstract [sv]

Ett Natural Language Interface är ett gränssnitt som tar indata i form av språk istället för detvanliga sättet med tangentbord och mus. Ett Natural Language Interface fungerar genom attdet först tar ut satsdelarna i indatan, och sedan omvandlar dessa satsdelar till logiska uttrycksom kan bearbetas. Effektiviteten och användbarheten hos Natural Language Interfacesjämfördes med det normala sättet att få indata i form av tangentbord och mus. Dettagenomfördes genom att testanvändare spelade ett spel med Natural Language Interface ochsedan köra deras använda indata genom en semantic parser. Resultaten indikerar att NaturalLanguage Interface i sitt nuvarande tillstånd är ett mindre effektivt sätt att få indata än detvanliga sättet med tangentbord och mus.

Place, publisher, year, edition, pages
2015. , 20 p.
National Category
Computer Science
URN: urn:nbn:se:kth:diva-166411OAI: diva2:810979
Available from: 2015-05-28 Created: 2015-05-08 Last updated: 2015-05-28Bibliographically approved

Open Access in DiVA

fulltext(552 kB)38 downloads
File information
File name FULLTEXT01.pdfFile size 552 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 38 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

Total: 129 hits
ReferencesLink to record
Permanent link

Direct link