P12-1039 proposes a data-driven method for concept-to-text generation , the task of automatically producing
N12-1093 approaches have emerged that tackle concept-to-text generation end-to-end . Due to the complexity
P03-1069 goals as is often the case in concept-to-text generation . Although in single document
J09-1003 development of both text-to-text and concept-to-text generation systems . 1 . Introduction Information
D15-1230 model . 2 Generation Framework In concept-to-text generation pipelines , discourse planning
N12-1093 Hypergraphs </title> Konstas Abstract Concept-to-text generation refers to the task of automatically
J09-1003 of an integrated approach for concept-to-text generation in which the same centering features
P12-1039 present a data-driven approach to concept-to-text generation that is domain - independent
P03-1069 ordering does not arise solely in concept-to-text generation but also in the emerging field
P03-1069 much attention in the area of concept-to-text generation ( see Reiter and Dale 2000 for
J05-3002 Generation Unlike traditional concept-to-text generation approaches , text-to-text generation
P12-1039 woman making the dress . <title> Concept-to-text Generation via Discriminative Reranking
D13-1157 <title> Inducing Document Plans for Concept-to-text Generation </title> Konstas Abstract In
J10-3005 labeling ( Punyakanok et al. 2004 ) , concept-to-text generation ( Marciniak and Strube 2005 ;
P09-1024 se - lection . In traditional concept-to-text generation , a content planner provides
E14-1053 translation models ( 5 ) ; and concept-to-text generation ( 16 ) . In our retrieval model
N12-1093 forecast generation . A typical concept-to-text generation system implements a pipeline
J09-1003 development in both text-to-text and concept-to-text generation . This work can be extended in
N12-1093 labeled data . 1 Introduction Concept-to-text generation broadly refers to the task of
J08-1001 ; this is an essential step in concept-to-text generation , multi-document summarization
hide detail