Tone restoration in transcribed Kammu: decision-list word sense disambiguation for an unwritten language
Författare
Redaktör
- Stephan Oepen
- Kristin Hagen
- Janne Bondi Johannessen
Summary, in English
The RWAAI (Repository and Workspace for Austroasiatic Intangible heritage) project aims at building a digital archive out of existing legacy data from the austroasiatic language family. One aspect of the project is the preservation of analogue legacy data. In this context, we have at our hands a large number of mostly-phonemic transcriptions of narrative monologues, often with accompanying sound recordings, in the unwritten Kammu language of northern Laos. Some of the transcriptions, however, lack tone marks, which for a tonal language such as Kammu makes them substantially less useful. The problem of restoring tones can be recast as one of word sense disambiguation, or, more generally, lexical ambiguity resolution. We attack it by decision lists, along the lines of Yarowsky (1994), using the tone-marked part of the corpus (120kW) as training data. The performance ceiling of this corpus is uncertain: the stories were all annotated, primarily for human rather than machine consumption, by a single person during almost 40 years, with slowly emerging idiosyncratic conventions. Thus, both inter-annotator and intra-annotator agreement figures are unknown. Nevertheless, with the data from this one annotator as a gold standard, we improve from an already-high baseline accuracy of 95.7% to 97.2% (by 10-fold cross-validation).
Avdelning/ar
Publiceringsår
2013
Språk
Engelska
Sidor
399-410
Publikation/Tidskrift/Serie
Linköping Electronic Conference Proceedings
Volym
85
Fulltext
- Available as PDF - 142 kB
- Download statistics
Länkar
Dokumenttyp
Konferensbidrag
Ämne
- General Language Studies and Linguistics
Nyckelord
- word sense disambiguation
- Kammu
- decision lists
- lexical ambiguity resolution
- tone restoration
- legacy data
Conference name
Nodalida 2013
Conference date
2013-05-23
Status
Published
ISBN/ISSN/Övrigt
- ISSN: 1650-3686
- ISSN: 1650-3740