Human dialogue is so complex that definitively analysing patterns of conversation may well be impossible. Within a conversation, all the complexities and ambiguities of natural la...
We present a fully automatic method for content selection evaluation in summarization that does not require the creation of human model summaries. Our work capitalizes on the assu...
Abstract. Automated language identification of written text is a wellestablished research domain that has received considerable attention in the past. By now, efficient and effecti...
This paper presents two methods which automatically produce annotated corpora for text summarisation on the basis of human abstracts. Both methods identify a set of sentences from ...
We consider the evaluation problem in Natural Language Generation (NLG) and present results for evaluating several NLG systems with similar functionality, including a knowledge-ba...