感情脆弱 发表于 2025-3-28 15:55:03

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

填满 发表于 2025-3-28 19:42:09

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 发表于 2025-3-29 02:23:05

http://reply.papertrans.cn/31/3089/308867/308867_43.png

Hormones 发表于 2025-3-29 03:30:45

http://reply.papertrans.cn/31/3089/308867/308867_44.png

健谈的人 发表于 2025-3-29 10:19:12

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

垄断 发表于 2025-3-29 13:24:31

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

多节 发表于 2025-3-29 17:13:01

http://reply.papertrans.cn/31/3089/308867/308867_47.png

滑动 发表于 2025-3-29 22:40:47

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 发表于 2025-3-30 02:04:39

http://reply.papertrans.cn/31/3089/308867/308867_49.png

碳水化合物 发表于 2025-3-30 05:53:10

http://reply.papertrans.cn/31/3089/308867/308867_50.png
页: 1 2 3 4 [5] 6
查看完整版本: Titlebook: Empirical Methods in Natural Language Generation; Data-oriented Method Emiel Krahmer,Mariët Theune Book 2010 Springer-Verlag Berlin Heidelb