论文信息 - A Discourse-based Approach to Generating Why-Questions from Texts

A Discourse-based Approach to Generating Why-Questions from Texts

We address the subtask of generating whyquestions from texts and propose the use of causal relations annotated in the Penn Discourse TreeBank for evaluating contentselection methods for why-question generation. Our initial experiments show that 71% of an independently developed data set of whyquestions can be correlated with causal relations annotated in the PDTB.

Rashmi Prasad

[1] Livio Robaldo,et al. The Penn Discourse TreeBank 2.0. , 2008, LREC.

[2] Beatrice Santorini,et al. Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[3] Lou Boves,et al. Discourse-based answering of why-questions , 2006, Trait. Autom. des Langues.

[4] Arthur C. Graesser,et al. Evaluation in Natural Language Generation : The Question Generation Task , 2007 .