Paper: Generating Discourse Structures For Written Text

ACL ID C04-1048
Title Generating Discourse Structures For Written Text
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2004

This paper presents a system for automati- cally generating discourse structures from written text. The system is divided into two levels: sentence-level and text-level. The sentence-level discourse parser uses syntactic information and cue phrases to segment sen- tences into elementary discourse units and to generate discourse structures of sentences. At the text-level, constraints about textual adja- cency and textual organization are integrated in a beam search in order to generate best dis- course structures. The experiments were done with documents from the RST Discourse Treebank. It shows promising results in a rea- sonable search space compared to the dis- course trees generated by human analysts.