Probabilistic Approaches for Modeling Text Structure and Their Application to Text-to-Text Generation

Abstract. Since the early days of generation research, it has been acknowledged that modeling the global structure of a document is crucial for producing coherent, readable output. However, traditional knowledgeintensive approaches have been of limited utility in addressing this problem since they cannot be effectively scaled to operate in domain-independent, large-scale applications. Due to this difficulty, existing text-to-text generation systems rarely rely on such structural information when producing an output text. Consequently, texts generated by these methods do not match the quality of those written by humans

• Type: Conference
• Year: 2010
• Where: EACL
• Authors: Regina Barzilay
• Keywords: EACL 2010, Natural Language Processing, Probabilistic Models, Text-to-text Generation Systems, Traditional Knowledgeintensive Approaches