Gold standard mappings created by experts are at the core of alignment evaluation. At the same time, the process of manual evaluation is rarely discussed. While the practice of ha...
Anna Tordai, Jacco van Ossenbruggen, Guus Schreibe...
A limitation of most speech recognizers is that they only recognize words from a fixed vocabulary. In this paper, we explore a technique for addressing this deficiency using aut...
Abstract—Vocabulary alignment is a main challenge in distributed access control as peers should understand each other’s policies unambiguously. Ontologies enable mutual underst...
Daniel Trivellato, Fred Spiessens, Nicola Zannone,...
Alignment combination (symmetrization) has been shown to be useful for improving Machine Translation (MT) models. Most existing alignment combination techniques are based on heuri...
The state-of-the-art system combination method for machine translation (MT) is the word-based combination using confusion networks. One of the crucial steps in confusion network d...