- Full text PDF available (3)
- This year (0)
- Last 5 years (4)
- Last 10 years (4)
Data Set Used
We describe the LIA machine translation systems for the Russian-English and English-Russian translation tasks. Various factored translation systems were built using MOSES to take into account the morphological complexity of Russian and we experimented with the romanization of un-translated Russian words.
Tag thunder is an audio version of a visual tag cloud content representation. Tag thunders aim to bring quick reading strategies, such as skimming, to blind people. Tag thunders vocalize the key terms of a page using concurrent speech paradigm coupled with additional audio effects, similar to visual effects in a tag cloud. In this paper we present our… (More)
As data-driven approaches started to make their way into the Natural Language Generation (NLG) domain, the need for automation of corpus building and extension became apparent. Corpus creation and extension in data-driven NLG domain traditionally involved manual paraphrasing performed by either a group of experts or with resort to crowd-sourcing. Building… (More)