Fully automatic multi-language translation with a catalogue of phrases – successful employment for the Swiss avalanche bulletin

K. Winkler, T. Kuhn

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

The Swiss avalanche bulletin is produced twice a day in four languages. Due to the lack of time available for manual translation, a fully automated translation system is employed, based on a catalogue of predefined phrases and predetermined rules of how these phrases can be combined to produce sentences. Because this catalogue of phrases is limited to a small sublanguage, the system is able to automatically translate such sentences from German into the target languages French, Italian and English without subsequent proofreading or correction. Having been operational for two winter seasons, we assess here the quality of the produced texts based on two different surveys where participants rated texts from real avalanche bulletins from both origins, the catalogue of phrases versus manually written and translated texts. With a mean recognition rate of 55 %, users can hardly distinguish between the two types of texts, and give very similar ratings with respect to their language quality. Overall, the output from the catalogue system can be considered virtually equivalent to a text written by avalanche forecasters and then manually translated by professional translators. Furthermore, forecasters declared that all relevant situations were captured by the system with sufficient accuracy. Forecaster’s working load did not change with the introduction of the catalogue: the extra time to find matching sentences is compensated by the fact that they no longer need to double-check manually translated texts. The reduction of daily translation costs is expected to offset the initial development costs within a few years.
Original languageEnglish
Pages (from-to)13-35
JournalLanguage Resources and Evaluation
Volume51
Issue number1
DOIs
Publication statusPublished - 2016

Fingerprint

bulletin
Swiss
language
French language
costs
translator
Language
rating
lack

Keywords

  • Machine translation
  • Catalogue of phrases
  • Controlled Natural Language
  • Text quality
  • Avalanche warning

Cite this

@article{1141c362e9eb46e8b198dca33d4fafbd,
title = "Fully automatic multi-language translation with a catalogue of phrases – successful employment for the Swiss avalanche bulletin",
abstract = "The Swiss avalanche bulletin is produced twice a day in four languages. Due to the lack of time available for manual translation, a fully automated translation system is employed, based on a catalogue of predefined phrases and predetermined rules of how these phrases can be combined to produce sentences. Because this catalogue of phrases is limited to a small sublanguage, the system is able to automatically translate such sentences from German into the target languages French, Italian and English without subsequent proofreading or correction. Having been operational for two winter seasons, we assess here the quality of the produced texts based on two different surveys where participants rated texts from real avalanche bulletins from both origins, the catalogue of phrases versus manually written and translated texts. With a mean recognition rate of 55 {\%}, users can hardly distinguish between the two types of texts, and give very similar ratings with respect to their language quality. Overall, the output from the catalogue system can be considered virtually equivalent to a text written by avalanche forecasters and then manually translated by professional translators. Furthermore, forecasters declared that all relevant situations were captured by the system with sufficient accuracy. Forecaster’s working load did not change with the introduction of the catalogue: the extra time to find matching sentences is compensated by the fact that they no longer need to double-check manually translated texts. The reduction of daily translation costs is expected to offset the initial development costs within a few years.",
keywords = "Machine translation, Catalogue of phrases, Controlled Natural Language, Text quality, Avalanche warning",
author = "K. Winkler and T. Kuhn",
year = "2016",
doi = "10.1007/s10579-015-9316-5",
language = "English",
volume = "51",
pages = "13--35",
journal = "Language Resources and Evaluation",
issn = "1574-020X",
publisher = "Springer Netherlands",
number = "1",

}

Fully automatic multi-language translation with a catalogue of phrases – successful employment for the Swiss avalanche bulletin. / Winkler, K.; Kuhn, T.

In: Language Resources and Evaluation, Vol. 51, No. 1, 2016, p. 13-35.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Fully automatic multi-language translation with a catalogue of phrases – successful employment for the Swiss avalanche bulletin

AU - Winkler, K.

AU - Kuhn, T.

PY - 2016

Y1 - 2016

N2 - The Swiss avalanche bulletin is produced twice a day in four languages. Due to the lack of time available for manual translation, a fully automated translation system is employed, based on a catalogue of predefined phrases and predetermined rules of how these phrases can be combined to produce sentences. Because this catalogue of phrases is limited to a small sublanguage, the system is able to automatically translate such sentences from German into the target languages French, Italian and English without subsequent proofreading or correction. Having been operational for two winter seasons, we assess here the quality of the produced texts based on two different surveys where participants rated texts from real avalanche bulletins from both origins, the catalogue of phrases versus manually written and translated texts. With a mean recognition rate of 55 %, users can hardly distinguish between the two types of texts, and give very similar ratings with respect to their language quality. Overall, the output from the catalogue system can be considered virtually equivalent to a text written by avalanche forecasters and then manually translated by professional translators. Furthermore, forecasters declared that all relevant situations were captured by the system with sufficient accuracy. Forecaster’s working load did not change with the introduction of the catalogue: the extra time to find matching sentences is compensated by the fact that they no longer need to double-check manually translated texts. The reduction of daily translation costs is expected to offset the initial development costs within a few years.

AB - The Swiss avalanche bulletin is produced twice a day in four languages. Due to the lack of time available for manual translation, a fully automated translation system is employed, based on a catalogue of predefined phrases and predetermined rules of how these phrases can be combined to produce sentences. Because this catalogue of phrases is limited to a small sublanguage, the system is able to automatically translate such sentences from German into the target languages French, Italian and English without subsequent proofreading or correction. Having been operational for two winter seasons, we assess here the quality of the produced texts based on two different surveys where participants rated texts from real avalanche bulletins from both origins, the catalogue of phrases versus manually written and translated texts. With a mean recognition rate of 55 %, users can hardly distinguish between the two types of texts, and give very similar ratings with respect to their language quality. Overall, the output from the catalogue system can be considered virtually equivalent to a text written by avalanche forecasters and then manually translated by professional translators. Furthermore, forecasters declared that all relevant situations were captured by the system with sufficient accuracy. Forecaster’s working load did not change with the introduction of the catalogue: the extra time to find matching sentences is compensated by the fact that they no longer need to double-check manually translated texts. The reduction of daily translation costs is expected to offset the initial development costs within a few years.

KW - Machine translation

KW - Catalogue of phrases

KW - Controlled Natural Language

KW - Text quality

KW - Avalanche warning

U2 - 10.1007/s10579-015-9316-5

DO - 10.1007/s10579-015-9316-5

M3 - Article

VL - 51

SP - 13

EP - 35

JO - Language Resources and Evaluation

JF - Language Resources and Evaluation

SN - 1574-020X

IS - 1

ER -