Article published in:
Written Language & Literacy
Vol. 19:2 (2016) ► pp. 157–188

SHOTGUN: converting words into triplets

A hybrid approach to grapheme-phoneme conversion in Dutch

| Radboud University Nijmegen
Software systems convert between graphemes and phonemes using lexicon-based, rule-based or data-driven techniques. SHOTGUN combines these techniques in a hybrid system which converts between graphemes and phonemes bi-directionally, adds linguistic and educational information about the relationships between graphemes and phonemes and provides estimates about the likelihood that the generated output is correct. We describe the components from which SHOTGUN is built and determine its accuracy by running tests on two data sources, the BasisSpellingBank and CELEX, comparing the results to Nunn’s (1998) rule-based conversion system. SHOTGUN converts phonemes to graphemes and vice versa with precision of 81% and 86% when tested on the BasisSpellingBank, and 80% and 81% when tested on CELEX. SHOTGUN proves to be a powerful new conversion tool.
Keywords: automatic bi-directional grapheme-phoneme conversion, Dutch language, grapheme-phoneme relationship, overlap algorithm, triplet analysis
Published online: 01 June 2017
https://doi.org/10.1075/wll.19.2.02bee
References
Busser, Bertjan, Walter Daelemans & Antal van den Bosch
(1999) Machine learning of word pronunciation: the case against abstraction. In Eurospeech 991: 2123–2126.Google Scholar
Cranshoff, Betty & Johan Zuidema
(2010) Van Dale Basisspellinggids. Utrecht/Antwerpen: Van Dale Lexicografie.Google Scholar
Daelemans, Walter
(1988)  grafon: a grapheme-to-phoneme conversion system for Dutch. Proceedings, 12th international conference on computational linguistics ( coling-88), vol. 11: 133–138.Google Scholar
Daelemans, Walter & Antal van den Bosch
(1993) Data-oriented methods for grapheme-to-phoneme conversion. Proceedings of eacl 61: 45–53.Google Scholar
(1997) Language-independent data-oriented grapheme-to-phoneme conversion. In Jan P.H. van Santen, Richard W. Sproat, Joseph P. Olive & Julia Hirschberg (eds.), Progress in speech synthesis, Section 2: 77–89. New York: Springer-Verlag. CrossrefGoogle Scholar
(2001)  treetalk: memory-based word phonemisation. In Robert I. Damper (ed.) Data-driven techniques in speech synthesis, Chapter 7. Cambridge: mit Press. CrossrefGoogle Scholar
Daelemans, Walter, Antal van den Bosch & Ton Weijters
(1996) IGTree: Using trees for compression and classification in lazy learning algorithms. Artificial Intelligence Review 111: 407–423. CrossrefGoogle Scholar
Daelemans, Walter & Helmer Strik
(2002) Het Nederlands in taal- en spraaktechnologie: prioriteiten voor basisvoorzieningen. Een rapport in opdracht van de Nederlandse Taalunie. Second version.Google Scholar
Damper, Robert & John Eastmond
(1997) Pronunciation by analogy: Impact of implementational choices on performance. Language and Speech 40(1): 1–23. CrossrefGoogle Scholar
Decadt, Bart, Jacques Duchateau, Walter Daelemans & Patrick Wamback
(2002) Memory-based phoneme-to-grapheme conversion. Language and Computers 45(1): 47–61.Google Scholar
Galescu, Lucian & James F. Allen
(2001) Bi-directional conversion between graphemes and phonemes using a joint n-gram model. Proceedings of the 4th ISCA Tutorial and Research Workshop on Speech Synthesis 41: 103–108.Google Scholar
Geeraerts, Dirk
(2002) Groot woordenboek van de Nederlandse taal ( cd-rom, version 1.0 Plus). Utrecht/Antwerpen: Van Dale Lexicografie.Google Scholar
Hamming, Richard
(1950) Error detecting and error correcting codes. Bell System Technical Journal 29(2): 147 – 160. CrossrefGoogle Scholar
Heemskerk, Josée & Wim Zonneveld
(2000) Uitspraakwoordenboek. Utrecht: Het Spectrum.Google Scholar
Hoste, Veronique, Steven Gillis & Walter Daelemans
(2000) Machine learning for modeling Dutch pronunciation variation. 10th Meeting on Computational Linguistics in the Netherlands: 73–84. Utrecht Institute of Linguistics OTS.Google Scholar
Jones, Daniel
(1996) Analogical natural language processing. London: ucl Press.Google Scholar
Jongenburger, Willy & Vincent J. van Heuven
(1993) Sandhi processes in natural and synthetic speech. In Vincent J. van Heuven & Louis C.W. Pols (eds.), Analysis and synthesis of speech, strategy research towards high quality text-to-speech-generation: 261–276. Berlin: Mouton de Gruyter. CrossrefGoogle Scholar
Levenshtein, Vladimir
(1966) Binary codes capable of correcting deletions, insertions, and reversals. Soviet Physics Doklady 10(8): 707 – 710.Google Scholar
Marchand, Yannick & Robert Damper
(2000) A multistrategy approach to improving pronunciation by analogy. Computational Linguistics 26(2): 195–219. CrossrefGoogle Scholar
Nunn, Anneke M.
(1998) Dutch orthography. A systematic investigation of the spelling of Dutch words (Doctoral dissertation). The Hague: Holland Academic Graphics.Google Scholar
Nunn, Anneke M. & Vincent J. van Heuven
(1993)  morphon: lexicon-based text-to-phoneme conversion and phonological rules. In Vincent J. van Heuven & Louis C.W. Pols (eds.), Analysis and synthesis of speech, strategy research towards high quality text-to-speech-generation: 77–99. Berlin: Mouton de Gruyter. CrossrefGoogle Scholar
Santen, Jan P.H. van, Richard W. Sproat, Joseph P. Olive & Julia Hirschberg
(1997) Progress in speech synthesis, Section 2. New York: Springer-Verlag. CrossrefGoogle Scholar
Skousen, Royal
(1989) Analogical modeling of language. Dordrecht: Kluwer Academic Publishers.Google Scholar
Zuidema, Johan & Anneke Neijt
(2012) Verkennend onderzoek naar de wenselijkheid en de haalbaarheid van een verrijking van de Woordenlijst Nederlandse Taal ten behoeve van spellingonderwijs. Nijmegen: Radboud Universiteit Nijmegen. Online available: http://​taalunieversum​.org​/sites​/tuv​/files​/downloads​/rapport%20VWS%2015022013​.pdf.
to appear). The BasisSpellingBank – spelling knowledge stored in a lexicon of triplets.
Cited by

Cited by 1 other publications

Zuidema, Johan & Anneke Neijt
2017. The BasisSpellingBank. Written Language & Literacy 20:1 ► pp. 52 ff. Crossref logo

This list is based on CrossRef data as of 11 november 2021. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.