Identifying discourse relations in a text is essential for various tasks in Natural Language Processing, such as automatic text summarization, question-answering, and dialogue gene...
Hugo Hernault, Danushka Bollegala, Mitsuru Ishizuk...
Articles in the Penn TreeBank were identified as being reviews, summaries, letters to the editor, news reportage, corrections, wit and short verse, or quarterly profit reports. Al...
We present a novel model to represent and assess the discourse coherence of text. Our model assumes that coherent text implicitly favors certain types of discourse relation transi...
This paper provides a solution to discourse structure adaptation in the process of automatic hypermedia presentation generation. Existing approaches to discourse structure composit...
Event extraction systems typically locate the role fillers for an event by analyzing sentences in isolation and identifying each role filler independently of the others. We argu...