German verbal inflection is frequently wrong in standard statistical machine translation approaches. German verbs agree with subjects in person and number, and they bear information about mood and tense. For subject-verb agreement, we parse German MT output to identify subject-verb pairs and ensure that the verb agrees with the subject. We show that this approach improves subject-verb agreement. We model tense/mood translation from English to German by means of a statistical classification model. Although our model shows good results on well-formed data, it does not systematically improve tense and mood in MT output. Reasons include the need for discourse knowledge, dependency on the domain, and stylistic variety in how tense/mood is translated. We present a thorough analysis of these problems.
展开▼
