Paraphrasing and Translation - part 9 pptx

comparison to the present comparison to the present situation 0.361comparison with the current situation 0.194relation to the situation we have at present 0.111... Example TranslationsTh

on the reform of the common tural policy

agricul-0.056

all the fundamental rights all the fundamental rights 0.8

comparison to the present comparison to the present situation 0.361

comparison with the current situation 0.194relation to the situation we have at

present

0.111

for small- and medium-sized enterprises 0.007

i can confirm i can confirm 0.899

meet the target meet the target 0.735

part of the agreement part of the agreement 0.739

the last issue the last issue 0.282

the part of individual the part of individual countries 0.5

the real choice the real choice 0.83

the conservative party in the unitedkingdom

0.063

thirteen years ago thirteen years ago 0.917

to the candidates themselves to the candidates themselves 0.778

wake up to this situation wake up 0.278

Example Translations

This Appendix gives a number of examples which illustrate the types of improvementsthat we get by integrating paraphrases into statistical machine translation The tablesshow example translations produced by the baseline system and by the paraphrasesystem when their translation models are trained on various sized parallel corpora.The translation models were trained on corpora containing 10,000, 20,000, 40,000,80,000, 160,000 and 320,000 sentence pairs (as described in Section 7.1) In addition

to the MT output we provide the source sentences and reference translations

The bold text is meant to highlight regions where the translations produced by theparaphrase system represent improvement in translation quality over the baseline sys-tem In some cases a particular source word is untranslated in the baseline, but istranslated by the paraphrase system For instance, in the first example in Table B.1the Spanish word altera is left untranslated by the baseline system, but the paraphrasesystem produces the English translation warning, which matches the reference trans-lation

In some cases neither the baseline system nor the paraphrase system manage totranslate a word For instance, in the same example as above, the Spanish word ven isleft untranslated by both systems Since the training data for the translation model was

so small, none of the paraphrases of ven had translations, thus the paraphrase systemperformed similarly to the baseline system We do not highlight these instances, since

we intended the bold text to be indicative of improved translations

167