Titlebook: Empirical Methods in Natural Language Generation; Data-oriented Method Emiel Krahmer,Mari?t Theune Book 2010 Springer-Verlag Berlin Heidelb

感情脆弱

Assessing the Trade-Off between System Building Cost and Output Quality in Data-to-Text Generationo create and maintain. Methods for automating (part of) the system building process exist, but do such methods risk a loss in output quality? In this paper, we investigate the cost/quality trade-off in generation system building. We compare six data-to-text systems which were created by predominantl

填滿

Human Evaluation of a German Surface Realisation Rankers sentences and automatically generated strings chosen by statistical models (language model, log-linear model), as well as the naturalness of the strings chosen by the log-linear model. We also investigate to what extent preceding context has an effect on choice. We show that native speakers do acc

Tailor

Hormones

健談的人

Introducing Shared Tasks to NLG: The TUNA Shared Task Evaluation Challenges been part of this development since its inception. This chapter looks back on the experience of organising the three . Challenges, which came to an end in 2009. While we discuss the role of the .s in yielding a substantial body of research on the . problem, which has opened new avenues for future r

壟斷

Generating Referring Expressions in Context: The GREC Task Evaluation Challengesmiliar discourse entities. In the . research programme we have been interested in a version of the . problem definition that is (i) grounded within discourse context, (ii) embedded within an application context, and (iii) informed by naturally occurring data. This paper provides an overview of our a

多節(jié)

滑動(dòng)

Generating Approximate Geographic Descriptions incorporates domain knowledge and task constraints to model the utility of a description. Our evaluations show that NLG systems, because they can analyse input data exhaustively, can produce more fine-grained geographic descriptions that are potentially more useful to end users than those generated by human experts.

天空

碳水化合物