We analyse the contribution of higher-level elements of the linguistic specification of a data-driven speech synthesiser to the naturalness of the synthetic speech which it genera...
We present a quasi-synchronous dependency grammar (Smith and Eisner, 2006) for machine translation in which the leaves of the tree are phrases rather than words as in previous wor...
This paper presents a fully automatic framework for the restoration of double-sided historical manuscripts which are impaired by ink bleed-through distortions. First, the recto si...
Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods...
Current statistical machine translation systems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment...