We present a novel method to improve word alignment quality and eventually the translation performance by producing and combining complementary word alignments for low-resource la...
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the b...
Tiffs lmper concerns an approach to Machine Translation whieJJ differs from the typical 'standard' approaches crucially in.that it does not rely on the prior existence o...
—Mobile robots that interact with humans in an intuitive way must be able to follow directions provided by humans in unconstrained natural language. In this work we investigate h...
To ensure the re-use of domain ontologies the usual approach relies on a pivot language, e.g., Kif, intoandfromwhich the domainontologyis translated. This requires several distinc...