Machine Translation

Topics

• Statistical machine translation
• Extension of translation memories
• Domain-speci c machine translation
• Machine translation between close languages
• Sub-word level machine translation

Statistical machine translation

Improving statistical machine translation

• free state-of-the-art tools available (SRILM, Moses)
• baseline SMT available for everyone
• languages with high number of wordforms need special treatment
• dělám, děláš, dělal, dělajícímu, dělaje, děláním, ...

magas, magasabb, legmagasabb, legeslegmagasabb, ...

• language models can be enriched with linguistic knowledge

Word alignment matrix - from words to phrases

Domain-speci c machine translation

• straightforward way of increasing quality of MT
• domain-speci c corpora can be downloaded on demand
• separate models for each domain: sports, cooking, gardening
• one sense per domain: bat

• translations of
  • product details, product descriptions in e-shops,
  • manuals, warranty certi cates,
  • user interface localizations, ...

Machine translation between close languages

• West and South Slavic languages: Czech, Slovak, Polish, Serbian, Croatian, Slovene
• MT mainly on word level, structure is very similar
• di erences can be described systematically by rules: hraje na klavíri <-> hraje na klavír
• billion-word corpora available for these languages
• dictionaries can be generated semi-automatically

• -> searching for duplicates in close languages (reprinted news)

MT quality, European languages

Sub-word level machine translation

• SMT principle applied on character level
• translation on subword level (English -> Czech)

• translation across levels

• -> translation of out-of-dictionary words

Conclusions

• generating new segments for translation memories
• domain-speci c translation
• translation between close languages
• sub-word level translation