Abstract for Multilingual Revision
European Workshop on Natural Language Generation

      Natural Language Generation has made great strides towards multilingual generation from large-scale knowledge sources. Meanwhile, current research in revision has vastly improved the quality of text that NLG systems produce. However, to-date there has been no attempt at combining revision and multilingual NLG. This paper presents research in multilingual revision, the last major pipelined NLG component to be studied from a multilingual perspective. We describe the linguistic difficulties in achieving multilingual revision, review recent work, and present an implemented framework for multilingual revision rules.




IRST/TCC Home