evaluating the fully automatic multi evaluating the fully
play

Evaluating the fully automatic multi Evaluating the fully automatic - PowerPoint PPT Presentation

Evaluating the fully automatic multi Evaluating the fully automatic multi- g g y y -language language g g g g translation of the Swiss avalanche bulletin translation of the Swiss avalanche bulletin Kurt Winkler 1 , Tobias Kuhn 2 ,


  1. Evaluating the fully automatic multi Evaluating the fully automatic multi- g g y y -language language g g g g translation of the Swiss avalanche bulletin translation of the Swiss avalanche bulletin Kurt Winkler 1 , Tobias Kuhn 2 , Martin Volk 3 1 WSL Institute for Snow and Avalanche Research SLF Switzerland 1 WSL Institute for Snow and Avalanche Research SLF, Switzerland 2 Department of Humanities, Social and Political Sciences, ETH Zurich, Switzerland 3 Universität Zürich, Institut für Computerlinguistik, Switzerland WSL Institute for Snow and Avalanche Research SLF

  2. Avalanches in Switzerland Avalanches in Switzerland Avalanches in Switzerland Avalanches in Switzerland 25 victims / year 25 victims / year avalanche bulletin • since 1945 • re-launch 2012 • www.slf.ch, app "White Risk", print...

  3. WSL-Institut für Schnee- und Lawinenforschung SLF 3

  4. WSL-Institut für Schnee- und Lawinenforschung SLF 4

  5. WSL-Institut für Schnee- und Lawinenforschung SLF 5

  6. danger description WSL-Institut für Schnee- und Lawinenforschung SLF 6

  7. snow cover and weather • evening (5 pm) i (5 ) • normally written and manually translated ll t l t d WSL-Institut für Schnee- und Lawinenforschung SLF 7

  8. Danger description • evening and morning (5 pm 8 am) evening and morning (5 pm, 8 am) • automated translation (catalogue of phrases)

  9. Automated translation Automated translation – why ? Automated translation Automated translation why ? why ? why ? New bulletin: all products in 4 languages • no additional money for translations Morning edition: field observations came in until issue Morning edition: field observations came in until issue time (8 am). • no time for manual translations ti f l t l ti • no time for proof-reed or corrections (in target languages) WSL-Institut für Schnee- und Lawinenforschung SLF

  10. Automated translation Automated translation Automated translation Automated translation Machine translation Machine translation • quality insufficient for life-critical warnings WSL-Institut für Schnee- und Lawinenforschung SLF 10

  11. Automated translation Automated translation Automated translation Automated translation Machine translation Machine translation • quality insufficient for life-critical warnings Memory system (translations of 15 years) • • Already used to reduce the translation time Already used to reduce the translation time. • Not comprehensive enough to extract a catalogue of phrases, or for statistical machine translation 1 or for statistical machine translation 1 Lepsus T., Langlais P. and Lapalme G., 2004. A corpus-based Approach to Weather Report WSL-Institut für Schnee- und Lawinenforschung SLF 11 Translation. Technical Report, University of Montréal, Canada.

  12. Automated translation Automated translation Automated translation Automated translation Machine translation Machine translation • quality insufficient for life-critical warnings Memory system (translations of 15 years) • • Already used to reduce the translation time. Already used to reduce the translation time • Not comprehensive enough to extract a catalogue of phrases, or for statistical machine translation 1 or for statistical machine translation Meteo Centrale: used for severe weather warnings ? ? Catalogue of phrases Catalogue of phrases • 1 Lepsus T., Langlais P. and Lapalme G., 2004. A corpus-based Approach to Weather Report Translation. Technical Report, University of Montréal, Canada.

  13. Catalogue Catalogue-based translation system Catalogue Catalogue based translation system based translation system based translation system • sentences = succession of segments g • segments = lists of predefined options • • translation must take place on the segment level translation must take place on the segment level • not all possible sentences are meaningful, but • all those that make sense must have correct translations ll th th t k t h t t l ti WSL-Institut für Schnee- und Lawinenforschung SLF 13

  14. Catalogue Catalogue Catalogue based translation system Catalogue-based translation system based translation system based translation system • sentences = succession of segments g • segments = lists of predefined options • • translation must take place on the segment level translation must take place on the segment level • not all possible sentences are meaningful, but • all those that make sense must have correct translations ll th th t k t h t t l ti • options can consist of series of sub-segments WSL-Institut für Schnee- und Lawinenforschung SLF 14

  15. Rules for Rules for the sentences Rules for Rules for the sentences the sentences in German the sentences in German in German in German No specific simplified grammar No specific simplified grammar.

  16. Rules for Rules for the sentences Rules for Rules for the sentences the sentences in German the sentences in German in German in German No specific simplified grammar No specific simplified grammar. Adjectives refer to subjects with the same gender and number in all the options (in each individual language) in all the options (in each individual language).  The translation of the subjects must already be known.

  17. Rules for Rules for the sentences Rules for Rules for the sentences the sentences in German the sentences in German in German in German No specific simplified grammar No specific simplified grammar. Adjectives refer to subjects with the same gender and number in all the options (in each individual language) in all the options (in each individual language). Articles and prepositions are usually included in the same option as the noun option as the noun. Segment 1 in the other regions on the northern Alpine ridge in Val Calanca

  18. Rules for the sentences in German Rules for the sentences in German Rules for the sentences in German Rules for the sentences in German Demonstrative pronouns substitute one specific noun It is Demonstrative pronouns substitute one specific noun. It is indicated in the editor. Segment 1 Avalanches Avalanches Wet avalanches S Snow drifts d ift  IT: "quest e ultim e " (feminine) They (="avalanches") They (="snow drifts")  IT: "quest i ultim i " (masculine)

  19. Catalogue Catalogue Catalogue Catalogue 110 sentences 110 sentences 1 to 10 segments 1 to 250 predefined options options can contain sub (sub )segments options can contain sub-(sub-)segments >> 1000000000000 different sentences possible WSL-Institut für Schnee- und Lawinenforschung SLF

  20. Translation of the catalogue Translation of the catalogue Translation of the catalogue Translation of the catalogue Manual translation allow Manual translation allow • replacing adjectives with participles or adverbs • active • active ↔ passive formulation passive formulation • synonyms WSL-Institut für Schnee- und Lawinenforschung SLF

  21. Translation of the catalogue Translation of the catalogue Translation of the catalogue Translation of the catalogue The segment order could vary between the languages The segment order could vary between the languages. (segments with 1 option must not be used in every language) (segments with 1 option must not be used in every language) (parts of the text can be relocated to other segments)

  22. Translation of the catalogue Translation of the catalogue Translation of the catalogue Translation of the catalogue The segment order could vary between the languages The segment order could vary between the languages. Each segment could be split in two. • target languages only • this limits our system to German  other languages

  23. Translation of the catalogue Translation of the catalogue Translation of the catalogue Translation of the catalogue The segment order could vary between the languages The segment order could vary between the languages. Each segment could be split in two. • target languages only • this limits our system to German  other languages No logical functions or distinction of cases.

  24. Translation of the catalogue Translation of the catalogue Translation of the catalogue Translation of the catalogue The segment order could vary between the languages The segment order could vary between the languages. Each segment could be split in two. • target languages only • this limits our system to German  other languages No logical functions or distinction of cases. Chef of the translation agency: Chef of the translation agency: "Stilt houses-technique" "Neanderthal man–technique"

  25. Operational service Operational service Operational service Operational service Editor with search engine Editor with search engine WSL-Institut für Schnee- und Lawinenforschung SLF

  26. Operational service Operational service Operational service Operational service Editor with search engine Editor with search engine Danger descriptions were proof-read and discussed by at least two avalanche forecasters (in German). WSL-Institut für Schnee- und Lawinenforschung SLF

Recommend


More recommend