Abstract
This paper describes some exploratory attempts to apply a combination of finite state
transducers (FST) and transformation-based learning (TBL, Brill 1992) to the problem of
letter-to-sound (LTS) conversion for Swedish. Following Bouma (2000) for Dutch, we employ
FST for segmentation of the textual input into groups of letters and a first transcription stage;
we feed the output of this step into a TBL system. With this setup, we reach 96.2% correctly
transcribed segments with rather restricted means (a small set of hand-crafted rules for the
FST stage; a set of 12 templates and a training set of 30kw for the TBL stage).
Observing that quantity is the major error source and that compound morpheme
boundaries can be useful for inferring quantity, we exploratively add good precision-low
recall compound splitting based on graphotactic constraints. With this simple-minded
method, targeting only a subset of the compounds, performance improves to 96.9%.
transducers (FST) and transformation-based learning (TBL, Brill 1992) to the problem of
letter-to-sound (LTS) conversion for Swedish. Following Bouma (2000) for Dutch, we employ
FST for segmentation of the textual input into groups of letters and a first transcription stage;
we feed the output of this step into a TBL system. With this setup, we reach 96.2% correctly
transcribed segments with rather restricted means (a small set of hand-crafted rules for the
FST stage; a set of 12 templates and a training set of 30kw for the TBL stage).
Observing that quantity is the major error source and that compound morpheme
boundaries can be useful for inferring quantity, we exploratively add good precision-low
recall compound splitting based on graphotactic constraints. With this simple-minded
method, targeting only a subset of the compounds, performance improves to 96.9%.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of Fonetik 2006 |
| Editors | Gilbert Ambrazaitis, Susanne Schötz |
| Publisher | Lund University |
| Pages | 141-144 |
| Publication status | Published - 2006 |
| Event | Fonetik 2006 - Hörsalen, SOL, Lunds Universitet, Helgonabacken 12, Lund, Sweden Duration: 2006 Jun 7 → 2006 Jun 9 |
Conference
| Conference | Fonetik 2006 |
|---|---|
| Country/Territory | Sweden |
| City | Lund |
| Period | 2006/06/07 → 2006/06/09 |
Bibliographical note
The information about affiliations in this record was updated in December 2015.The record was previously connected to the following departments: Linguistics and Phonetics (015010003)
Subject classification (UKÄ)
- General Language Studies and Linguistics
Free keywords
- LTS
- Swedish
- grapheme-to-phoneme conversion for Swedish
- letter-to-sound conversion for Swedish