作者: Paul Piwek , Svetlana Stoyanchev
DOI:
关键词:
摘要: Generating expository dialogue from monologue is a task that poses an interesting and rewarding challenge for Natural Language Processing. This short paper has three aims: firstly, to motivate the importance of this task, both in terms benefits as way present information potential applications; secondly, introduce parallel corpus monologues dialogues which enables data-driven approach challenge; and, finally, describe work-in-progress on semi-automatic construction Monologue-to-Dialogue (M2D) generation rules.