Tone restoration in transcribed Kammu: decision-list word sense disambiguation for an unwritten language
(2013) Nodalida 2013 85. p.399-410- Abstract
- 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... (More)
- 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). (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3800276
- author
- Uneson, Marcus LU
- organization
- publishing date
- 2013
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- word sense disambiguation, Kammu, decision lists, lexical ambiguity resolution, tone restoration, legacy data
- host publication
- Linköping Electronic Conference Proceedings
- editor
- Oepen, Stephan ; Hagen, Kristin and Bondi Johannessen, Janne
- volume
- 85
- pages
- 399 - 410
- conference name
- Nodalida 2013
- conference dates
- 2013-05-23
- ISSN
- 1650-3686
- 1650-3740
- language
- English
- LU publication?
- yes
- additional info
- 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)
- id
- b3c199bf-ea4d-4891-a6a6-dd6349a54da8 (old id 3800276)
- alternative location
- http://www.ep.liu.se/ecp_article/index.en.aspx?issue=085;article=036
- date added to LUP
- 2016-04-04 08:33:51
- date last changed
- 2018-11-21 20:49:36
@inproceedings{b3c199bf-ea4d-4891-a6a6-dd6349a54da8, abstract = {{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).}}, author = {{Uneson, Marcus}}, booktitle = {{Linköping Electronic Conference Proceedings}}, editor = {{Oepen, Stephan and Hagen, Kristin and Bondi Johannessen, Janne}}, issn = {{1650-3686}}, keywords = {{word sense disambiguation; Kammu; decision lists; lexical ambiguity resolution; tone restoration; legacy data}}, language = {{eng}}, pages = {{399--410}}, title = {{Tone restoration in transcribed Kammu: decision-list word sense disambiguation for an unwritten language}}, url = {{https://lup.lub.lu.se/search/files/5185029/3800349.pdf}}, volume = {{85}}, year = {{2013}}, }